Triple
T28632848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gryffindor Quidditch Chaser (reserve in films) |
E724691
|
entity |
| Predicate | teamCaptainInSomeFilms |
P14876
|
FINISHED |
| Object | Harry Potter |
—
|
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: Harry Potter | Statement: [Gryffindor Quidditch Chaser (reserve in films), teamCaptainInSomeFilms, Harry Potter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: teamCaptainInSomeFilms Context triple: [Gryffindor Quidditch Chaser (reserve in films), teamCaptainInSomeFilms, Harry Potter]
-
A.
filmCaptainActor
Indicates that the actor plays the role of a captain in the specified film.
-
B.
hasDirectorStar
Indicates that a person both directed and starred in the same work (e.g., film, show, or production).
-
C.
teamCaptain
chosen
Indicates that one entity serves as the captain or designated leader of a particular team.
-
D.
leadActorAlsoDirector
Indicates that the person who plays the lead acting role in a production is also the director of that same production.
-
E.
associatedWithLeadActorOfFilm
Indicates a relationship where one entity is connected or linked in some relevant way to the lead actor of a specified film.
- 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_69f01d8328c48190bc0e5f9b9b848582 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f6691f5e188190b12c7b2eb729a45e |
completed | May 2, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69f6659b62fc8190b21555d0ba54db2d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 4:38 a.m.