Triple
T18070979
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fred Done |
E432426
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Peter Done |
—
|
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 Done | Statement: [Fred Done, sibling, Peter Done]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peter Done Context triple: [Fred Done, sibling, Peter Done]
-
A.
Peter Done
chosen
Peter Done is a British businessman best known as the co-founder of the major UK bookmaker Betfred.
-
B.
Harry Torczyner
Harry Torczyner, better known as Naftali Herz Tur-Sinai, was a prominent Jewish philologist and Bible scholar who played a key role in the revival and standardization of Modern Hebrew.
-
C.
Peter Braun
Peter Braun is a relatively obscure individual whose primary public association is sharing the surname Braun, with no widely recognized distinguishing achievements or roles.
-
D.
Peter V. Daniel
Peter V. Daniel was a 19th-century American jurist who served as an Associate Justice of the U.S. Supreme Court and was known for his pro-slavery and states’ rights opinions.
-
E.
Stephen Poliakoff
Stephen Poliakoff is a British playwright, screenwriter, and director known for his distinctive, character-driven television dramas and films.
- 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_69d8b9070cac81909fa9473fb1c3f1c7 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ccee2fa4819098a61f7fdb8f1853 |
completed | April 19, 2026, 12:39 p.m. |
Created at: April 10, 2026, 10:26 a.m.