Triple
T17247388
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jim Broadbent |
E418662
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Broadbent |
E418662
|
NE 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: Broadbent | Statement: [Jim Broadbent, familyName, Broadbent]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Broadbent Context triple: [Jim Broadbent, familyName, Broadbent]
-
A.
Broadbent
chosen
Broadbent is an English surname borne by various notable individuals, including acclaimed actor Jim Broadbent.
-
B.
Blurton
Blurton is a suburban area in Stoke-on-Trent, Staffordshire, England, known primarily as a residential community.
-
C.
Brockhart
Brockhart is a family surname, notably associated with the character Ted Brockhart.
-
D.
Bennett
Bennett is a common English-language surname of Anglo-Norman origin borne by numerous notable individuals across politics, arts, and sciences.
-
E.
Bennett
Bennett is the main villain and former comrade-turned-mercenary antagonist who battles Arnold Schwarzenegger’s character in the 1985 action film "Commando."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d886d9ab108190b70edd8d17aa1204 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42e24a4508190bbcc70c36b2b9c13 |
completed | April 19, 2026, 1:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0170f744d8819099f10bbba364586d |
completed | May 11, 2026, 6:02 a.m. |
Created at: April 10, 2026, 5:39 a.m.