Triple
T7403349
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eccles Line |
E170803
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Eccles |
E5767
|
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: Eccles | Statement: [Eccles Line, connects, Eccles]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eccles Context triple: [Eccles Line, connects, Eccles]
-
A.
Eccles
chosen
Eccles is a town in Greater Manchester, England, known for its historic market and the traditional Eccles cake.
-
B.
Eccles
Eccles is a small unincorporated coal-mining community located in Raleigh County, West Virginia.
-
C.
Eccles
Eccles is a small village in Kent, England, situated near the River Medway within the Tonbridge and Malling district.
-
D.
Southchurch
Southchurch is a suburban area within the town of Southend-on-Sea in Essex, England, known for its residential character and local amenities.
-
E.
Churche
Churche is an alternative spelling variant of the word "Church," typically referring to a Christian place of worship or the associated religious institution.
- 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_69c68a6010108190925e5284de022660 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f26ea27c8190a55e0e0314b463d8 |
completed | March 27, 2026, 9:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c81ed79680819087a56082e968c266 |
completed | March 28, 2026, 6:32 p.m. |
Created at: March 27, 2026, 3:10 p.m.