Triple
T23032634
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mayor of Kingstown |
E573503
|
entity |
| Predicate | composer |
P1361
|
FINISHED |
| Object | Andrew Lockington |
—
|
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: Andrew Lockington | Statement: [Mayor of Kingstown, composer, Andrew Lockington]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andrew Lockington Context triple: [Mayor of Kingstown, composer, Andrew Lockington]
-
A.
Andrew Lockington
chosen
Andrew Lockington is a Canadian film composer known for his orchestral scores for major action and adventure movies, including the disaster film "San Andreas."
-
B.
Richard Lestock
Richard Lestock was an 18th-century British Royal Navy admiral best known for his controversial role in the War of the Austrian Succession and the ensuing court-martial over his conduct in battle.
-
C.
Andrew Lancaster
Andrew Lancaster is a musician and composer known for creating the music for the film "Garage Days."
-
D.
Richard Hiscott
Richard Hiscott is an editor known for his work on the television series "Willow."
-
E.
Richard Laxton
Richard Laxton is a British film and television director known for his work on dramas such as the period film "Effie Gray."
- 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_69e245b911188190bc3d96326c847969 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f184822a90819081907d72c76770b0 |
completed | April 29, 2026, 4:09 a.m. |
Created at: April 17, 2026, 3:53 p.m.