Triple
T8171478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roz Doyle |
E190830
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | David Angell |
E214171
|
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 Angell | Statement: [Roz Doyle, creator, David Angell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Angell Context triple: [Roz Doyle, creator, David Angell]
-
A.
David Angell
chosen
David Angell was an American television producer and writer best known as a co-creator of the hit sitcoms "Frasier" and "Wings."
-
B.
David Duffield
David Duffield is an American billionaire entrepreneur and philanthropist best known for founding the enterprise software companies PeopleSoft and Workday.
-
C.
David Allison
David Allison is a technology entrepreneur best known as one of the founders of the early semiconductor company Signetics.
-
D.
Stephen Langridge
Stephen Langridge is a British opera and theatre director known for leading major European opera institutions and for his innovative, often socially engaged productions.
-
E.
Christopher Gunning
Christopher Gunning was a British composer best known for his film and television scores, including the iconic theme for the detective series "Poirot."
- 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_69ca82c1c0a08190bf8692b4d91a03ca |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb48056d0c819094575090a41e0083 |
completed | March 31, 2026, 4:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccbf5cfd588190b12ef9b5799ffd88 |
completed | April 1, 2026, 6:46 a.m. |
Created at: March 30, 2026, 5:39 p.m.