Editing Openai/69186d20-2d14-8013-b9c6-c09000f173f6 (section)

=== Assistant: 2511141615ET ===
251114_1615ET

good question, and we’re now in the “deep structure of Celtic consonants” zone.

I’ll separate:
# Does a fortis/lenis contrast in sonorants still ''live'' in modern Irish?
# How it relates to historical gemination.

==== Short version: yes, but it’s weak, gradient, and largely allophonic; the only really robust contrast is broad vs slender. ====

Historically, Old Irish had:
* “Fortis” sonorants: written ll, mm, nn, rr after vowels.
* “Lenis” sonorants: written single l, m, n, r.

By late Old Irish:
* The length contrast (true gemination) in these was basically gone.
* BUT the quality difference remained: - fortis vs lenis sonorants differed in tensity, timing, and maybe length of the preceding vowel. - Think “stronger, tighter closure, more consonant-y” vs “weaker, shorter, more glidy”.

In Modern Irish:
* You still get traces of this, particularly in r and sometimes n, l: - word-internally, rr vs r, nn vs n can feel “stronger vs weaker” to native speakers in some dialects.
* But for practical phonology: - the active phonemic contrasts are broad vs slender, not fortis vs lenis. - fortis/lenis sonorants are at most subphonemic and dialect-specific; not something the standard orthography tries to maintain consistently as a live contrast.

So:

: 

==== Timeline, very compressed: ====
# Proto-Celtic / early Old Irish - Had real geminate consonants: /ll, nn, mm, rr/ with extra duration. - These came from: - inherited IE geminates, - assimilation across morpheme boundaries, - analogical formations.
# Old Irish - Geminate vs single distinction in sonorants gets reinterpreted: - Geminate ll, nn, mm, rr → “fortis” sonorants (stronger, tenser) - Single l, n, m, r → “lenis” (weaker) - At this stage, length is no longer the main cue; you get a bundled cluster of phonetic effects (duration, articulation, maybe lowering of preceding vowel). - Crucially: this fortis/lenis contrast is now phonemic in some positions.
# Middle → Modern Irish - The functional load of fortis vs lenis shrinks: - Many former contrasts are lost or neutralized in common environments. - Broad vs slender becomes the salient contrast (and is reinforced by spelling). - Orthography keeps ll, nn, mm, rr in lots of places, but now the fortis realization is mostly reduced to subtle timing/quality differences, not a clear-cut second parameter.

So to your specific options:

: 

Best description:
* There was true gemination originally.
* The geminate vs non-geminate contrast then turned into a fortis vs lenis contrast (same segment quality axis, different primary cue: tensity rather than raw length).
* That fortis/lenis contrast has since been mostly absorbed into: - broad vs slender, - general timing/strength patterns, - and lexicalized idiosyncrasies.

So: fortis sonorants are historically “ex-geminates”. They’re not some independent ancient tense/lenis system that gemination later merged into; rather, gemination was reanalysed as “fortis”, and then the phonetic salience of this fortisness has faded over time.

==== - For learning/pronouncing Irish now, you can safely ignore fortis vs lenis and just track: - broad vs slender consonants - length/quality of vowels ====
* The double consonant in a word like Spáinn: - is not telling you “geminate” in a phonetic sense, - and not truly giving you a live fortis vs lenis opposition either, - it’s mostly historic spelling + analogy.
* If you want to model nuance, you can think: - nn, ll, rr often realized slightly tenser or shorter-voweled than single ones, but that’s detail, not a rule you must obey to be understood.

So:

>