Triple
T28135115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marathon Man universe |
E714177
|
entity |
| Predicate | filmNotableActor |
P29643
|
FINISHED |
| Object | Laurence Olivier |
—
|
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: Laurence Olivier | Statement: [Marathon Man universe, filmNotableActor, Laurence Olivier]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filmNotableActor Context triple: [Marathon Man universe, filmNotableActor, Laurence Olivier]
-
A.
notableStar
Indicates that the subject is a star (or stellar object) that is distinguished or noteworthy in some significant way, such as brightness, fame, or scientific interest, relative to other stars.
-
B.
notableDirector
Indicates that a person has directed a work (such as a film or show) in a way that is recognized as significant or distinguished.
-
C.
madeFamousByFilm
Indicates that something became widely known or gained significant public recognition as a result of being featured in a film.
-
D.
filmAssociatedWith
chosen
Indicates a general relationship or connection between a film and another entity, such as a person, organization, event, or work.
-
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_69efd6af156c81908f50c2cd7db0e1ef |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f6412eece8819083585f8d75aff17d |
completed | May 2, 2026, 6:23 p.m. |
| PD | Predicate disambiguation | batch_69f63c6a8474819091b8c6fe98e3862d |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 9:49 p.m.