Triple
T22948246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rosewood |
E569933
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Gregory Poirier |
—
|
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: Gregory Poirier | Statement: [Rosewood, screenwriter, Gregory Poirier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gregory Poirier Context triple: [Rosewood, screenwriter, Gregory Poirier]
-
A.
Gregory Poirier
chosen
Gregory Poirier is an American screenwriter and producer known for his work on numerous Hollywood films and television projects.
-
B.
Dustin Poirier
Dustin Poirier is an American mixed martial artist and former interim UFC Lightweight Champion known for his high-level striking, durability, and victories over numerous elite opponents.
-
C.
Anthony Pettis
Anthony Pettis is an American mixed martial artist and former UFC lightweight champion known for his dynamic striking and highlight-reel kicks.
-
D.
Dan Ige
Dan Ige is an American mixed martial artist and UFC featherweight contender known for his relentless pace, durability, and well-rounded skill set.
-
E.
Jérémy Lauzon
Jérémy Lauzon is a Canadian professional ice hockey defenceman who has played in the NHL for teams including the Boston Bruins, Nashville Predators, and Seattle Kraken.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2459199d08190a8184ee2aa935842 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1819fbf8c8190ad80c93f1507aa73 |
completed | April 29, 2026, 3:57 a.m. |
Created at: April 17, 2026, 3:46 p.m.