Triple
T17599907
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bulls |
E428665
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Marton |
—
|
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: Marton | Statement: [Bulls, locatedNear, Marton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marton Context triple: [Bulls, locatedNear, Marton]
-
A.
Marton
chosen
Marton is a rural service town in New Zealand’s North Island, located in the Rangitīkei District of the Manawatū-Whanganui region.
-
B.
Marton
Marton is a masculine given name of Hungarian origin, borne by various notable individuals including actors and athletes.
-
C.
Marton village
Marton village is a small rural settlement in North Yorkshire, England, known for its historic parish church of St Cuthbert and traditional countryside character.
-
D.
Garstang
Garstang is a small historic market town in Lancashire, England, known for its rural charm and location between the River Wyre and the Forest of Bowland.
-
E.
Mirfeld
Mirfeld is a small settlement that forms part of the municipality of Amel in eastern Belgium.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d889e1c6148190ba76241e74688f8b |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46c4812d48190bf8e899fa8f7fbe4 |
completed | April 19, 2026, 5:46 a.m. |
Created at: April 10, 2026, 5:51 a.m.