Triple
T7191367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Winner |
E167698
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Hannibal Brooks |
E648286
|
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: Hannibal Brooks | Statement: [Michael Winner, directed, Hannibal Brooks]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hannibal Brooks Context triple: [Michael Winner, directed, Hannibal Brooks]
-
A.
Hannibal Brooks
chosen
Hannibal Brooks is a 1969 British war comedy film about a prisoner of war who escapes through the Alps with an elephant, directed by Michael Winner and starring Oliver Reed.
-
B.
Slimm Calhoun
Slimm Calhoun is an American rapper from Atlanta best known for his work with the Dungeon Family collective and his early-2000s solo material.
-
C.
Blackford Oakes
Blackford Oakes is a fictional American CIA agent and Cold War spy created by William F. Buckley Jr.
-
D.
Isham Randolph
Isham Randolph was an 18th-century Virginia planter and sea captain, best known as the grandfather of U.S. President Thomas Jefferson.
-
E.
Abner Nash
Abner Nash was an American lawyer and politician who served as the second governor of North Carolina during the Revolutionary War era.
- 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_69c6888b5248819090499a884ee3ec39 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e90087208190a65e49ae0e8a7cbf |
completed | March 27, 2026, 8:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7cbe39e6881909d65aa44ba4273a1 |
completed | March 28, 2026, 12:38 p.m. |
Created at: March 27, 2026, 2:50 p.m.