Triple
T8190226
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maurice |
E191283
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Richard Robbins |
E117453
|
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: Richard Robbins | Statement: [Maurice, musicBy, Richard Robbins]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Richard Robbins Context triple: [Maurice, musicBy, Richard Robbins]
-
A.
Richard Robbins
chosen
Richard Robbins was an American film composer best known for his long-standing collaboration with Merchant Ivory Productions, scoring acclaimed period dramas such as "Howards End" and "The Remains of the Day."
-
B.
Michael Krieger
Michael Krieger is a fictional character appearing in the story of "Watch Over Me."
-
C.
David Shaw
David Shaw was an American screenwriter known for his work in mid-20th-century film and television.
-
D.
David Shaw
David Shaw is an American football coach best known for his successful tenure as head coach of Stanford University's football program in the 2010s.
-
E.
Ken Scott
Ken Scott is a Canadian screenwriter and director known for films such as "Starbuck," "Delivery Man," and "The Grand Seduction."
- 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_69ca82c5b6948190a583c096fb0a6c71 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4da2f4108190b9b69cb7f41ef374 |
completed | March 31, 2026, 4:29 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cced8da28c81909c34c0103da68f0f |
completed | April 1, 2026, 10:03 a.m. |
Created at: March 30, 2026, 5:41 p.m.