Triple
T17640145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taaffe |
E429201
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | Peter Taaffe |
—
|
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: Peter Taaffe | Statement: [Taaffe, hasNotableBearer, Peter Taaffe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peter Taaffe Context triple: [Taaffe, hasNotableBearer, Peter Taaffe]
-
A.
Peter Taaffe
chosen
Peter Taaffe is a British Trotskyist politician and writer best known as a leading figure of the Militant tendency and later the Socialist Party (England and Wales).
-
B.
Chris Taaffe
Chris Taaffe is a film and television producer known for working on the acclaimed drama "Prayers for Bobby."
-
C.
Pat Taaffe
Pat Taaffe was a renowned Irish National Hunt jockey best known for his partnership with the legendary steeplechaser Arkle and multiple major race victories in the 1960s.
-
D.
Patrick Friesacher
Patrick Friesacher is an Austrian racing driver best known for competing in Formula One during the 2005 season.
-
E.
Peter Mathieson
Peter Mathieson is a British nephrologist and academic leader who has served as principal and vice-chancellor of major universities, including the University of Edinburgh and the University of Hong Kong.
- 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_69d889e2c2608190b762e76d9b2262f1 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46de50bf481909e938613b38f0202 |
completed | April 19, 2026, 5:53 a.m. |
Created at: April 10, 2026, 6:02 a.m.