Triple
T7335552
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sands of Iwo Jima |
E169117
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Edmund Grainger |
E515059
|
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: Edmund Grainger | Statement: [Sands of Iwo Jima, producer, Edmund Grainger]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Edmund Grainger Context triple: [Sands of Iwo Jima, producer, Edmund Grainger]
-
A.
Edmund Grainger
chosen
Edmund Grainger was an American film producer active during Hollywood’s studio era, known for overseeing numerous features including notable war and adventure films.
-
B.
Richard Grainger
Richard Grainger was a 19th-century British builder and developer renowned for reshaping central Newcastle upon Tyne with elegant neoclassical streets and buildings.
-
C.
John Bevan
John Bevan was a British intelligence officer who played a key role in planning and overseeing Allied deception operations during World War II.
-
D.
William Praed
William Praed was a prominent English banker and politician of the late 18th and early 19th centuries.
-
E.
David Farrar
David Farrar is a Canadian academic and administrator who serves as the president and vice-chancellor of McMaster University.
- 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_69c68a568a6481908f11e20db7bc8446 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f0c38d6c81908a57ef1eea0e4951 |
completed | March 27, 2026, 9:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7ef22d6ac819087f05d6e6787509a |
completed | March 28, 2026, 3:09 p.m. |
Created at: March 27, 2026, 3:04 p.m.