Triple
T3310758
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Milford Haven |
E69564
|
entity |
| Predicate | hasNearbyTown |
P3883
|
FINISHED |
| Object | Haverfordwest |
E208720
|
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: Haverfordwest | Statement: [Milford Haven, hasNearbyTown, Haverfordwest]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Haverfordwest Context triple: [Milford Haven, hasNearbyTown, Haverfordwest]
-
A.
Haverfordwest
chosen
Haverfordwest is a historic market town in southwest Wales that serves as the principal commercial and administrative centre of Pembrokeshire.
-
B.
Amlwch
Amlwch is a small coastal town in northern Anglesey, Wales, historically known for its copper mining and maritime heritage.
-
C.
Carmarthen
Carmarthen is a historic market town in southwest Wales, often regarded as one of the oldest towns in the country and traditionally linked with the legends of Merlin.
-
D.
Penryn
Penryn is a historic town and former parliamentary borough in Cornwall, England.
-
E.
Pwllheli
Pwllheli is a coastal market town and popular seaside resort on the Llŷn Peninsula in Gwynedd, northwest Wales.
- 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_69ad859f218081909458d2cebbf57565 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb0ec80508190baa78435b983b7b5 |
completed | March 8, 2026, 5:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5b73c409081909c583019d7ec1d4a |
completed | March 14, 2026, 7:30 p.m. |
Created at: March 8, 2026, 3:11 p.m.