Triple
T9736484
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portsmouth North |
E236075
|
entity |
| Predicate | neighbouringConstituency |
P47257
|
FINISHED |
| Object | Havant |
E133361
|
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: Havant | Statement: [Portsmouth North, neighbouringConstituency, Havant]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Havant Context triple: [Portsmouth North, neighbouringConstituency, Havant]
-
A.
Havant
chosen
Havant is a market town and borough in south-east England, situated between Portsmouth and Chichester near the south coast.
-
B.
Fareham
Fareham is a market town in southern England situated between the cities of Southampton and Portsmouth.
-
C.
Basingstoke
Basingstoke is a large town in Hampshire, England, known as a major commercial and retail centre with significant modern development and transport links.
-
D.
Waterlooville
Waterlooville is a town in Hampshire, England, situated north of Portsmouth and known primarily as a residential and commuter area.
-
E.
Farnham
Farnham is a historic market town in southern England known for its Georgian streets, medieval castle, and surrounding Surrey countryside.
- 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_69ca84d313e88190983ee6ffd0ef60d2 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9ef032088190acd94c35b89e48b7 |
completed | April 1, 2026, 10:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1cc408b988190980db82fbd93e988 |
completed | April 5, 2026, 2:43 a.m. |
Created at: March 30, 2026, 8:22 p.m.