Triple
T950577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Lyon |
E20510
|
entity |
| Predicate | placeOfActivity |
P1527
|
FINISHED |
| Object | Harrow |
E56899
|
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: Harrow | Statement: [John Lyon, placeOfActivity, Harrow]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harrow Context triple: [John Lyon, placeOfActivity, Harrow]
-
A.
Harrow
chosen
Harrow is a suburban district in northwest London, England, known for its historic town center and the prestigious Harrow School.
-
B.
Harrow East
Harrow East is a UK parliamentary constituency in northwest London, covering part of the suburban area within the London Borough of Harrow.
-
C.
West Harrow
West Harrow is a suburban residential area in northwest London, known for its local park, conservation area streets, and access to central London via the Metropolitan line.
-
D.
Harrow West
Harrow West is a UK parliamentary constituency in northwest London, covering part of the suburban area within the London Borough of Harrow.
-
E.
North Harrow
North Harrow is a suburban residential district in northwest London known for its local shopping area, transport links, and community amenities.
- 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_69a493b0f2fc81908cd227480a5356a1 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b3d62e408190855b2883407f6c6b |
completed | March 1, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acce513848819094ad79eea2a53172 |
completed | March 8, 2026, 1:18 a.m. |
Created at: March 1, 2026, 7:40 p.m.