Triple
T7280234
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Strahan |
E163127
|
entity |
| Predicate | businessPartner |
P282
|
FINISHED |
| Object | Andrew Millar |
E144802
|
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: Andrew Millar | Statement: [William Strahan, businessPartner, Andrew Millar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andrew Millar Context triple: [William Strahan, businessPartner, Andrew Millar]
-
A.
Andrew Millar
chosen
Andrew Millar was an 18th-century Scottish-born London bookseller and publisher known for issuing major works of Enlightenment authors, including David Hume.
-
B.
Francis McAvennie
Francis McAvennie is a former Scottish professional footballer best known as a prolific striker for clubs such as West Ham United and Celtic during the 1980s.
-
C.
Gavin Millar
Gavin Millar was a Scottish film and television director, critic, and producer known for his work on British dramas and literary adaptations.
-
D.
Andy MacMillan
Andy MacMillan was a prominent Scottish architect known for his influential modernist church and public building designs in the mid-20th century.
-
E.
Daniel Millar
Daniel Millar is an actor known for his role in the National Theatre’s acclaimed stage production of "Frankenstein."
- 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_69c6885c5964819085b209701769877f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6eb339b1081909f648864e210f98e |
completed | March 27, 2026, 8:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c810bb0d808190b6ade5592fce2c15 |
completed | March 28, 2026, 5:32 p.m. |
Created at: March 27, 2026, 2:59 p.m.