Triple
T5384581
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sands of Iwo Jima |
E113171
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | James Brown |
E467708
|
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: James Brown | Statement: [Sands of Iwo Jima, starring, James Brown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: James Brown Context triple: [Sands of Iwo Jima, starring, James Brown]
-
A.
James Brown
James Brown was an American publisher and co-founder of the prominent publishing house Little, Brown and Company in the 19th century.
-
B.
James Brown
James Brown is a British architect best known as a partner at the London-based practice Brown and Storey Architects.
-
C.
James Brown
James Brown is an American sportscaster best known as a longtime studio host for NFL coverage on major television networks.
-
D.
James Brown
James Brown is a songwriter credited as one of the writers of the hip-hop track "No Church in the Wild" by Jay-Z and Kanye West.
-
E.
James Brown
chosen
James Brown was an American actor known for his roles in mid-20th-century films and television, including war and Western genres.
- 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_69bd4436a1988190af18dcff7fd306b4 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd86f39edc81908e53973cef1bc0f3 |
completed | March 20, 2026, 5:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf295030b081909bea5e946aac098b |
completed | March 21, 2026, 11:27 p.m. |
Created at: March 20, 2026, 2:03 p.m.