Triple
T10858219
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Metrolink Airport line |
E256323
|
entity |
| Predicate | via |
P5680
|
FINISHED |
| Object | Peel Hall |
E35106
|
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: Peel Hall | Statement: [Metrolink Airport line, via, Peel Hall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peel Hall Context triple: [Metrolink Airport line, via, Peel Hall]
-
A.
Peel Hall
chosen
Peel Hall is a tram stop on Greater Manchester’s Metrolink light rail network, located on the Airport Line.
-
B.
Peel Hall
Peel Hall is a residential area within the Wythenshawe district of Manchester, England.
-
C.
Pound Hall
Pound Hall is a major academic and administrative building at Harvard Law School that houses classrooms, faculty offices, and legal research facilities.
-
D.
Blakesley Hall
Blakesley Hall is a well-preserved Tudor-era timber-framed manor house in Birmingham, England, now functioning as a historic house museum.
-
E.
Holker Hall
Holker Hall is a historic country house and estate in Cumbria, England, long associated with the Cavendish family and noted for its grand architecture and extensive gardens.
- 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_69d6aa83d1448190a66d93c32394d21f |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d751377da88190a7244bb9d6b0c2ec |
completed | April 9, 2026, 7:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69deb1a0a9188190be0e9677884f3e93 |
completed | April 14, 2026, 9:29 p.m. |
Created at: April 8, 2026, 9:20 p.m.