Triple
T2980222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lockerbie |
E80490
|
entity |
| Predicate | hasNearbyCity |
P350
|
FINISHED |
| Object | Dumfries |
E275099
|
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: Dumfries | Statement: [Lockerbie, hasNearbyCity, Dumfries]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dumfries Context triple: [Lockerbie, hasNearbyCity, Dumfries]
-
A.
Dumfries
chosen
Dumfries is a historic market town in southwest Scotland, serving as a regional hub for education, commerce, and culture in Dumfries and Galloway.
-
B.
Dumfries
Dumfries is a small historic town in Prince William County, Virginia, considered one of the oldest continuously chartered towns in the United States.
-
C.
Dunfermline
Dunfermline is a historic Scottish town and former royal capital known for its medieval abbey and rich cultural heritage.
-
D.
Kirriemuir
Kirriemuir is a small historic town in eastern Scotland, best known as the birthplace of Peter Pan author J. M. Barrie.
-
E.
Kilwinning
Kilwinning is a historic Scottish town in North Ayrshire, noted for its medieval abbey and strong connections to early Freemasonry.
- 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_69ad8b15f6ac8190be5fd16a33edcb4f |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad999e91788190a2d430dd0600a660 |
completed | March 8, 2026, 3:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bdd33296a08190b0d3cd9f7a5374a0 |
completed | March 20, 2026, 11:07 p.m. |
Created at: March 8, 2026, 2:58 p.m.