Triple
T4193044
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pete's Dragon |
E89078
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Daniel Hart |
E254796
|
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: Daniel Hart | Statement: [Pete's Dragon, musicBy, Daniel Hart]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Daniel Hart Context triple: [Pete's Dragon, musicBy, Daniel Hart]
-
A.
Daniel Hart
chosen
Daniel Hart is an American composer and musician known for his evocative film scores and frequent collaborations with director David Lowery.
-
B.
David Kraft
David Kraft is a member of the prominent Kraft family, known for its significant influence in the American food industry and philanthropy.
-
C.
Charles Hart
Charles Hart is a British lyricist best known for writing the lyrics to Andrew Lloyd Webber’s hit musical "The Phantom of the Opera."
-
D.
Leonard Rosenman
Leonard Rosenman was an American composer best known for his innovative, modernist film and television scores in the 1950s and beyond.
-
E.
Alan Siegel
Alan Siegel is a film producer best known for his long-running collaboration with actor Gerard Butler on action and thriller movies.
- 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_69aed9569a4481908b6c1fcec2a11e21 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0342c6048190835631649a14d304 |
completed | March 9, 2026, 5:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5db77e7d88190a7ba250972e133fa |
completed | March 14, 2026, 10:04 p.m. |
Created at: March 9, 2026, 3:46 p.m.