Triple
T9506668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harry Gregg |
E229286
|
entity |
| Predicate | transferFeeToManchesterUnited |
P13531
|
FINISHED |
| Object | 23000 pounds sterling |
—
|
LITERAL 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: 23000 pounds sterling | Statement: [Harry Gregg, transferFeeToManchesterUnited, 23000 pounds sterling]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transferFeeToManchesterUnited Context triple: [Harry Gregg, transferFeeToManchesterUnited, 23000 pounds sterling]
-
A.
BarcelonaTransferFee
Indicates the amount of money paid as a transfer fee in a football (soccer) transaction involving FC Barcelona.
-
B.
joinedManchesterUnited
chosen
Indicates that an entity became a member of, or signed to play for, Manchester United.
-
C.
signedForRealMadridForFee
Indicates that a person joined Real Madrid by signing a contract in exchange for a specified transfer fee.
-
D.
foreignTransactionFee
Indicates that a fee is charged for processing a transaction involving a foreign currency or occurring outside the cardholder’s home country.
-
E.
leftManchesterUnited
Indicates that an entity departed from or is no longer a member of Manchester United.
- F. None of above.
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_69ca847611c48190a28c028644198c75 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9852b7e48190a8f69cbde10d2858 |
completed | April 1, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69cca567ca448190bf4bcce8ce7dd54f |
completed | April 1, 2026, 4:56 a.m. |
Created at: March 30, 2026, 7:57 p.m.