Triple
T19061352
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yellow Route |
E466539
|
entity |
| Predicate | serves |
P98
|
FINISHED |
| Object | Hillsborough |
—
|
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: Hillsborough | Statement: [Yellow Route, serves, Hillsborough]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hillsborough Context triple: [Yellow Route, serves, Hillsborough]
-
A.
Hillsborough
Hillsborough is a historic football stadium in Sheffield, England, best known as the long-time home of Sheffield Wednesday F.C.
-
B.
Hillsborough
Hillsborough is a historic village in County Down, Northern Ireland, known for Hillsborough Castle, the official royal residence in Northern Ireland.
-
C.
Hillsborough
Hillsborough is the main town and administrative center of the Caribbean island of Carriacou in Grenada.
-
D.
Hillsborough
Hillsborough is a small village in southeastern New Brunswick, Canada, known for its rural character and proximity to the Bay of Fundy.
-
E.
Hillsborough
Hillsborough is a historic small town in North Carolina known for its well-preserved 18th- and 19th-century architecture and rich colonial and Revolutionary War heritage.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69d8dd040fb881909af2a964f65ad208 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e194c854819085a0a48d22c5cebd |
completed | April 20, 2026, 8:19 a.m. |
Created at: April 10, 2026, 12:03 p.m.