Triple
T15193876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Goin' South |
E363094
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Harry Gittes |
E821518
|
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: Harry Gittes | Statement: [Goin' South, producer, Harry Gittes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harry Gittes Context triple: [Goin' South, producer, Harry Gittes]
-
A.
Harry Gittes
chosen
Harry Gittes is a film producer best known for his work on notable American movies such as "About Schmidt."
-
B.
J. J. Gittes
J. J. Gittes is the cynical yet principled private investigator portrayed by Jack Nicholson in the classic neo-noir film "Chinatown."
-
C.
Harry Caul
Harry Caul is a reclusive, morally conflicted surveillance expert whose obsessive dedication to privacy and professional detachment drives the psychological tension in the film.
-
D.
Harry Block
Harry Block is the neurotic, self-absorbed writer protagonist of Woody Allen’s film "Deconstructing Harry," whose chaotic personal life fuels his fiction.
-
E.
Jack Crawford
Jack Crawford is a seasoned FBI agent and head of the Behavioral Science Unit who mentors Clarice Starling in Thomas Harris’s Hannibal Lecter novels and their film adaptations.
- 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_69d85a09a39c81908759f23268e2d408 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0067eb710819085211fd05d5fa5f0 |
completed | April 15, 2026, 9:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69feef66b4f08190a072332123253166 |
completed | May 9, 2026, 8:25 a.m. |
Created at: April 10, 2026, 3:10 a.m.