Triple
T12399532
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eugene Gant |
E296212
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Gant |
E471205
|
NE 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: Gant | Statement: [Eugene Gant, familyName, Gant]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gant Context triple: [Eugene Gant, familyName, Gant]
-
A.
Gant
chosen
Gant is a surname most notably associated with American character actor Richard Gant, known for his roles in film and television since the 1980s.
-
B.
Gant
Gant is a locality in the Swiss Alps situated close to the Findel Glacier, known as a starting point for alpine hiking and mountaineering routes.
-
C.
Gage
Gage is a surname of English origin borne by various notable individuals, including historical and contemporary figures.
-
D.
Tailo
Tailo is a widely used Latin-based romanization system for writing Taiwanese Hokkien, employed in education, literature, and language preservation.
-
E.
Bleret
Bleret is a locality or district within the municipality of Waremme in the province of Liège, Belgium.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6ad9f464c81909db36d7e96e34b9e |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d9401cbfd481908ee6e765da3d12cb |
completed | April 10, 2026, 6:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63482af8c8190b277b36371979f5e |
completed | May 2, 2026, 5:29 p.m. |
Created at: April 8, 2026, 9:55 p.m.