Triple
T23070695
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dave Hirsh |
E575184
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | James Jones |
—
|
NE NERFINISHED |
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: James Jones | Statement: [Dave Hirsh, creator, James Jones]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: James Jones Context triple: [Dave Hirsh, creator, James Jones]
-
A.
James Jones
James Jones is an architect known for his work on the Gallery of Modern Art.
-
B.
James Jones
James Jones is a retired United States Marine Corps general who served as President Barack Obama’s National Security Advisor.
-
C.
James Jones
James Jones was an American novelist and screenwriter best known for his World War II-themed works such as "From Here to Eternity."
-
D.
James Jones
James Jones is a former NBA player who became a basketball executive and now leads the Phoenix Suns’ front office.
-
E.
James Jones
James Jones is a British Anglican bishop and public figure known for leading the Hillsborough Independent Panel’s investigation into the 1989 football stadium disaster.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
Provenance (2 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_69e245bd6e4c8190bb8942245b68cad5 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18c5f17348190ab92cfdae9bcaeba |
completed | April 29, 2026, 4:43 a.m. |
Created at: April 17, 2026, 3:56 p.m.