Triple
T10751019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Killer Joe |
E253570
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Mimi Polk Gitlin |
E732989
|
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: Mimi Polk Gitlin | Statement: [Killer Joe, producer, Mimi Polk Gitlin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mimi Polk Gitlin Context triple: [Killer Joe, producer, Mimi Polk Gitlin]
-
A.
Mimi Polk Gitlin
chosen
Mimi Polk Gitlin is a film producer best known for her work on the acclaimed 1991 road movie "Thelma & Louise."
-
B.
Marya Mannes
Marya Mannes was an American writer, critic, and social commentator known for her sharp wit and incisive observations on mid-20th-century culture and politics.
-
C.
Ann Turkel
Ann Turkel is an American actress and former model known for her film and television roles in the 1970s and 1980s.
-
D.
Anna Scher
Anna Scher is a British drama teacher and theatre director best known for founding the influential Anna Scher Theatre in London, which has trained many prominent actors.
-
E.
Toni Stern
Toni Stern is an American lyricist best known for co-writing several of Carole King’s classic songs, including major tracks on the landmark album "Tapestry."
- 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_69d6aa5e51e8819095f06881cecf152e |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d71dc0ad188190b747bf9d10cf5de5 |
completed | April 9, 2026, 3:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de23292f8c8190a52c94c03e7d476d |
completed | April 14, 2026, 11:21 a.m. |
Created at: April 8, 2026, 9:15 p.m.