Triple
T17764757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harold Bishop |
E443474
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | David Bishop |
—
|
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: David Bishop | Statement: [Harold Bishop, relative, David Bishop]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Bishop Context triple: [Harold Bishop, relative, David Bishop]
-
A.
David Bishop
chosen
David Bishop is a New Zealand-born writer and former comics editor best known for his work on the British science fiction anthology 2000 AD and related tie-in novels.
-
B.
Andy Bishop
Andy Bishop is a professional English footballer known for his career as a striker in the lower tiers of the English football league system.
-
C.
Daron Bishop
Daron Bishop is a relatively obscure individual whose primary noted distinction is sharing the surname Bishop, with limited widely known public information available about him.
-
D.
Chris Bishop
Chris Bishop is a television producer best known for his work as an executive producer on the ABC sitcom "The Goldbergs."
-
E.
Keith Bishop
Keith Bishop is a socially awkward and bumbling accountant character from the British television mockumentary series "The Office."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d8b9edf16c8190a59ebd245d378f4f |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e485fb2a3c81908887d1d36aee942d |
completed | April 19, 2026, 7:36 a.m. |
Created at: April 10, 2026, 10:11 a.m.