Triple
T3342287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poltergeist |
E70286
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Michael Kahn |
E255464
|
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: Michael Kahn | Statement: [Poltergeist, editedBy, Michael Kahn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Kahn Context triple: [Poltergeist, editedBy, Michael Kahn]
-
A.
Michael Kahn
chosen
Michael Kahn is an acclaimed American film editor best known for his long-time collaboration with director Steven Spielberg on numerous major films.
-
B.
Ian Kahn
Ian Kahn is an American actor best known for playing George Washington on the television series "Turn: Washington's Spies."
-
C.
Marty Katz
Marty Katz is a film producer known for his work on movies such as the World War II drama "The Great Raid."
-
D.
Andrew Weisblum
Andrew Weisblum is an American film editor known for his work on major feature films, including collaborations with directors like Darren Aronofsky and Wes Anderson.
-
E.
Bruce Kimmel
Bruce Kimmel is an American writer, director, and Grammy-nominated record producer best known for his work in musical theatre and film, as well as for producing numerous cast albums.
- 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_69ad85a405e48190b6e68de7cf9f319e |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb1ee711481909c0d921f1b5b8562 |
completed | March 8, 2026, 5:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4c3667a288190aa79835f5d621942 |
completed | March 14, 2026, 2:09 a.m. |
Created at: March 8, 2026, 3:12 p.m.