Triple
T6371377
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Closeburn |
E143351
|
entity |
| Predicate | hasPostTown |
P2711
|
FINISHED |
| Object | Thornhill |
E307330
|
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: Thornhill | Statement: [Closeburn, hasPostTown, Thornhill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thornhill Context triple: [Closeburn, hasPostTown, Thornhill]
-
A.
Thornhill
Thornhill is a suburban community in the Greater Toronto Area known for its diverse population, residential neighborhoods, and proximity to Toronto.
-
B.
Thornhill
chosen
Thornhill is a small village in Dumfries and Galloway, Scotland, known for its rural character and proximity to the River Nith.
-
C.
Richmond Hill
Richmond Hill is a picturesque area in southwest London known for its famous panoramic views over the River Thames and surrounding landscape.
-
D.
Richmond Hill
Richmond Hill is a small coastal city in southeastern Georgia known for its proximity to Savannah and its historic ties to industrialist Henry Ford.
-
E.
Richmond Hill
Richmond Hill is a residential neighborhood in the borough of Queens, New York City, known for its diverse population and mix of historic homes and commercial corridors.
- 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_69c008d8c61081908bcaf61510d881ed |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c068289eac8190a17affed87340c1f |
completed | March 22, 2026, 10:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6386f361c819098dbe01b0cb07b06 |
completed | March 27, 2026, 7:57 a.m. |
Created at: March 22, 2026, 4:33 p.m.