Triple
T14712251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Losers |
E345576
|
entity |
| Predicate | editor |
P1954
|
FINISHED |
| Object | David Checel |
E467287
|
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: David Checel | Statement: [The Losers, editor, David Checel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Checel Context triple: [The Losers, editor, David Checel]
-
A.
David Checel
chosen
David Checel is a film editor known for his work on major Hollywood productions, including the 2010 action film "The Losers."
-
B.
John Burzichelli
John Burzichelli is an American Democratic politician from New Jersey who has served in the New Jersey General Assembly and held various local government positions.
-
C.
Christian Baute
Christian Baute is a film producer known for his work on the psychological thriller "Funny Games U.S."
-
D.
Marcus Raboy
Marcus Raboy is an American music video and film director known for his work with major hip-hop and R&B artists.
-
E.
Rob Beschizza
Rob Beschizza is a writer, editor, and designer best known for his work as a co-editor of the influential tech and culture blog Boing Boing.
- 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_69d822e4a8c08190a155df736bb7bc13 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb982bf248190881e21a8a0861a3f |
completed | April 14, 2026, 10:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fdf08f2aa08190a5ac3240d1de90fb |
completed | May 8, 2026, 2:17 p.m. |
Created at: April 10, 2026, 1:28 a.m.