Triple
T21079276
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mid Ulster District |
E519316
|
entity |
| Predicate | containsSettlement |
P847
|
FINISHED |
| Object | Pomeroy |
—
|
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: Pomeroy | Statement: [Mid Ulster District, containsSettlement, Pomeroy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pomeroy Context triple: [Mid Ulster District, containsSettlement, Pomeroy]
-
A.
Pomeroy
chosen
Pomeroy is a small village in County Tyrone, Northern Ireland, known for its rural setting and surrounding upland landscapes.
-
B.
Pomeroy
Pomeroy is a small rural town in KwaZulu-Natal, South Africa, known for its Zulu cultural heritage and agricultural surroundings.
-
C.
Pomeroy
Pomeroy is a surname of English origin that appears as the middle name of the British Army officer George Pomeroy Colley.
-
D.
Pomeroy’s
Pomeroy’s was a regional American department store chain known for selling a wide range of apparel and household goods before being absorbed into larger retail brands.
-
E.
Wentworthe
Wentworthe is an alternative historical or variant spelling of the English surname Wentworth.
- 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_69e0b506e59c8190849b71ed07929215 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e702d939e08190a37d7b7cc1872ad5 |
completed | April 21, 2026, 4:53 a.m. |
Created at: April 16, 2026, 2:49 p.m.