Triple
T9825214
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hoosiers |
E238637
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Carter De Haven |
E484030
|
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: Carter De Haven | Statement: [Hoosiers, producer, Carter De Haven]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carter De Haven Context triple: [Hoosiers, producer, Carter De Haven]
-
A.
Carter De Haven
chosen
Carter De Haven was an American actor, comedian, and film director active in the early to mid-20th century, known for his work in both silent and sound films.
-
B.
Carter Verone
Carter Verone is the ruthless Argentine drug lord and primary antagonist in the film "2 Fast 2 Furious."
-
C.
Carter Heywood
Carter Heywood is a witty, openly gay minority affairs liaison in the sitcom "Spin City," known for his sharp humor and social conscience.
-
D.
Carter Chambers
Carter Chambers is a terminally ill mechanic and family man who embarks on a globe-trotting adventure to fulfill his "bucket list" alongside a wealthy stranger in the film "The Bucket List."
-
E.
Joseph Carter
Joseph Carter is the author whose life story and writings about boxer Jake LaMotta inspired the film "Raging Bull."
- 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_69ca84e0dd1881909800765d1e21f735 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb3181c688190afea3b27ee392a30 |
completed | April 2, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1d5b9110881909405d94e0db40eac |
completed | April 5, 2026, 3:23 a.m. |
Created at: March 30, 2026, 8:31 p.m.