Triple
T7182170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Starbucks |
E167473
|
entity |
| Predicate | coFounder |
P2835
|
FINISHED |
| Object | Gordon Bowker |
E167473
|
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: Gordon Bowker | Statement: [Starbucks, coFounder, Gordon Bowker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gordon Bowker Context triple: [Starbucks, coFounder, Gordon Bowker]
-
A.
Gordon Bowker
chosen
Gordon Bowker is an American writer and entrepreneur best known as one of the co-founders of the global coffee company Starbucks.
-
B.
Gordon Juckes
Gordon Juckes was a prominent Canadian ice hockey administrator who played a key role in developing and promoting amateur hockey across Canada.
-
C.
Gordon Dawson
Gordon Dawson is an American screenwriter and producer best known for his collaborations with director Sam Peckinpah on films such as "Bring Me the Head of Alfredo Garcia."
-
D.
Gordon Hales
Gordon Hales was a film editor known for his work on major British and international productions, including Charlie Chaplin’s final film "A Countess from Hong Kong."
-
E.
Martin Boddey
Martin Boddey was a British character actor known for his frequent supporting roles in mid-20th-century films and television, often portraying authority figures such as policemen and officials.
- 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_69c6888a7c548190a3d39b52a393080f |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e8bc25088190a7d7f3ba2461b5e9 |
completed | March 27, 2026, 8:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7d37cfb8c8190a788dcaa1080fb0b |
completed | March 28, 2026, 1:11 p.m. |
Created at: March 27, 2026, 2:49 p.m.