Triple
T19959566
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aigues-Mortais |
E479774
|
entity |
| Predicate | correspondingFemininePluralForm |
P107812
|
FINISHED |
| Object | Aigues-Mortaises |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Aigues-Mortaises | Statement: [Aigues-Mortais, correspondingFemininePluralForm, Aigues-Mortaises]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: correspondingFemininePluralForm Context triple: [Aigues-Mortais, correspondingFemininePluralForm, Aigues-Mortaises]
-
A.
genderedPluralForm
chosen
Indicates that the plural form of a term is specifically marked or inflected to reflect a particular gender.
-
B.
hasFeminineFormInSomeLanguages
Indicates that the referenced entity has a distinct feminine grammatical or lexical form in at least one language.
-
C.
hasFemaleFormOf
Indicates that one entity is the specifically female version or form of another, more general or differently gendered entity.
-
D.
hasFeminineFormInCzechAndSlovak
Indicates that an entity has a specifically feminine grammatical or lexical form in the Czech and Slovak languages.
-
E.
pluralMasculineForm
Indicates that the referenced term is expressed in its plural form specifically for masculine grammatical gender.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8e523c19881909f9197037200dde6 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65af386548190aefac1e40aac403d |
completed | April 20, 2026, 4:57 p.m. |
| PD | Predicate disambiguation | batch_69e537f7e4848190b431a69ec3f1b609 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:54 p.m.