Triple
T18177426
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heller |
E435198
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | Paul Heller |
—
|
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: Paul Heller | Statement: [Heller, hasNotableBearer, Paul Heller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Heller Context triple: [Heller, hasNotableBearer, Paul Heller]
-
A.
Paul Heller
chosen
Paul Heller is a film producer best known for his work on influential cult movies, including the British black comedy "Withnail & I."
-
B.
Paul M. Heller
Paul M. Heller was an American film producer known for his work on influential independent and studio films, including the psychological drama "David and Lisa."
-
C.
Ben Heller
Ben Heller is an actor best known for playing young Stanley Uris in the 1990 television miniseries adaptation of Stephen King’s "It."
-
D.
Paul Frommer
Paul Frommer is a linguist best known for inventing the Na'vi language for James Cameron's film "Avatar."
-
E.
Paul Hollander
Paul Hollander was a Hungarian-American sociologist and author best known for his critical analyses of communism, political ideology, and intellectuals’ attitudes toward totalitarian regimes.
- 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_69d8b90c7ec081909b4694ccecb449c6 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4df5a72008190bd2e56205b995a87 |
completed | April 19, 2026, 1:57 p.m. |
Created at: April 10, 2026, 10:31 a.m.