Triple
T29035963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tullia |
E737858
|
entity |
| Predicate | romanFeminineForm |
P78555
|
FINISHED |
| Object | Tullia |
—
|
NE NERFINISHED |
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: Tullia | Statement: [Tullia, romanFeminineForm, Tullia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: romanFeminineForm Context triple: [Tullia, romanFeminineForm, Tullia]
-
A.
hasFemaleFormOf
chosen
Indicates that one entity is the specifically female version or form of another, more general or differently gendered entity.
-
B.
romanNomen
Indicates that an entity has a specific Roman nomen, i.e., the clan or gens name within the traditional Roman naming system.
-
C.
hasFeminineFormInSomeLanguages
Indicates that the referenced entity has a distinct feminine grammatical or lexical form in at least one language.
-
D.
latinGenitive
Indicates that one entity is in the Latin genitive case in relation to another, typically expressing possession, origin, or association.
-
E.
genderedFormOf
Indicates that one term is a gender-specific variant or inflected form corresponding to another, more neutral or differently gendered term.
- 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_69f077efb3848190b41574e1670f6ae2 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f674e06c9481909ed0ea736408f0d7 |
completed | May 2, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69f673c4abec8190bc2379e66f4af0a9 |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 28, 2026, 9:58 a.m.