Triple
T19587766
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | African Association |
E470147
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | James Phillips |
—
|
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 Phillips | Statement: [African Association, foundedBy, James Phillips]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: James Phillips Context triple: [African Association, foundedBy, James Phillips]
-
A.
James Phillips
James Phillips is a songwriter best known for his work on the track "So Excited."
-
B.
James Phillips
chosen
James Phillips was an 18th-century British Quaker abolitionist and publisher who played a key role in the early organized campaign to end the transatlantic slave trade.
-
C.
James Robert Phillips
James Robert Phillips was a British colonial officer best known for leading the ill-fated 1897 mission to the Kingdom of Benin that precipitated the punitive Benin Expedition.
-
D.
Jerry Phillips
Jerry Phillips is the son of influential American record producer Sam Phillips, founder of Sun Records.
-
E.
James Philbin
James Philbin is a computer vision researcher associated with the University of Oxford’s Visual Geometry Group, known for his work on image recognition and related machine learning methods.
- 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_69d8e510024481908415c0d616fa6186 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e64052f61c81908bb49927d4246030 |
completed | April 20, 2026, 3:03 p.m. |
Created at: April 10, 2026, 1:43 p.m.