Triple
T9795367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | I Shot an Arrow into the Air |
E237703
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Dewey Martin |
E602023
|
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: Dewey Martin | Statement: [I Shot an Arrow into the Air, castMember, Dewey Martin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dewey Martin Context triple: [I Shot an Arrow into the Air, castMember, Dewey Martin]
-
A.
Dewey Martin
Dewey Martin was a Canadian drummer best known for his work with the influential 1960s rock band Buffalo Springfield.
-
B.
Dewey Martin
chosen
Dewey Martin was an American film and television actor active in the 1950s and 1960s, known for roles in adventure and war dramas.
-
C.
Greg DePaul
Greg DePaul is an American screenwriter and playwright best known for co-writing the romantic comedy film "Bride Wars."
-
D.
Michael Dewell
Michael Dewell is best known as the husband of Dutch-American actress Nina Foch.
-
E.
Bill DeRonde
Bill DeRonde is a film editor best known for his work on the cult action film "The Boondock Saints."
- 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_69ca84dc04488190b9c91193976c0960 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda34916dc8190acef2ba003e56a33 |
completed | April 1, 2026, 10:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1cc5118a481908a65d730f86c7723 |
completed | April 5, 2026, 2:43 a.m. |
Created at: March 30, 2026, 8:28 p.m.