Triple
T2087159
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A49 road |
E45377
|
entity |
| Predicate | connectsTown |
P845
|
FINISHED |
| Object | Hereford |
E65056
|
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: Hereford | Statement: [A49 road, connectsTown, Hereford]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hereford Context triple: [A49 road, connectsTown, Hereford]
-
A.
Hereford
chosen
Hereford is a cathedral city in Herefordshire, England, known for its historic architecture and role as a military and agricultural center.
-
B.
Wellington, Shropshire
Wellington, Shropshire is a historic market town in Shropshire, England, now part of the new town of Telford.
-
C.
Swindon
Swindon is a large town in Wiltshire, England, known as a major commercial and commuter hub in the southwest with strong railway and industrial heritage.
-
D.
Bridgwater
Bridgwater is a historic market town in Somerset, England, known for its maritime heritage and role in regional trade and industry.
-
E.
Banbury
Banbury is a historic market town in Oxfordshire, England, known for its medieval cross, canal-side setting, and association with the traditional Banbury cake.
- 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_69a8891869c88190a02643e3bb746f59 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abba5641208190b925676b8d80f300 |
completed | March 7, 2026, 5:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae58c7cb408190bceee60492292f63 |
completed | March 9, 2026, 5:21 a.m. |
Created at: March 4, 2026, 7:41 p.m.