Triple
T19753958
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matt Haig |
E474456
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Matt Haig |
—
|
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: Matt Haig | Statement: [Matt Haig, name, Matt Haig]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matt Haig Context triple: [Matt Haig, name, Matt Haig]
-
A.
Matt Haig
chosen
Matt Haig is a British author known for his bestselling novels and non-fiction works that often explore mental health, time, and the human condition, including "The Midnight Library" and "Reasons to Stay Alive."
-
B.
Mitchell Burgess
Mitchell Burgess is an American television writer and producer best known for his work on the acclaimed HBO series *The Sopranos*.
-
C.
Mark Haddon
Mark Haddon is a British author best known for his award-winning novel "The Curious Incident of the Dog in the Night-Time," which has been widely acclaimed and adapted for stage and screen.
-
D.
Michael Grant
Michael Grant is a relatively private individual best known in public records as the former husband of Athena Grant.
-
E.
Michael Grant
Michael Grant is an American rock guitarist and singer best known for his work with the hard rock band L.A. Guns.
- 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_69d8e51940a0819087bd2996f98da668 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6529cae048190b4f8e6ba409bcf8e |
completed | April 20, 2026, 4:21 p.m. |
Created at: April 10, 2026, 1:48 p.m.