Triple
T22307144
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Komatsu |
E551408
|
entity |
| Predicate | hasSisterCity |
P919
|
FINISHED |
| Object | Gateshead |
—
|
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: Gateshead | Statement: [Komatsu, hasSisterCity, Gateshead]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gateshead Context triple: [Komatsu, hasSisterCity, Gateshead]
-
A.
Gateshead
chosen
Gateshead is a large town in northeast England, situated on the southern bank of the River Tyne opposite Newcastle upon Tyne, known for its modern architecture and cultural venues.
-
B.
Gateshead
Gateshead is a residential suburb in the City of Lake Macquarie, near Newcastle in New South Wales, Australia.
-
C.
Wallsend
Wallsend is a town in North Tyneside, England, historically significant as the eastern terminus of Hadrian’s Wall and site of the Segedunum Roman Fort.
-
D.
Wallsend
Wallsend is an electoral district in the New South Wales Legislative Assembly, representing a suburban area in the city of Newcastle, Australia.
-
E.
Washington, Tyne and Wear
Washington, Tyne and Wear is a town in North East England that forms part of the City of Sunderland and is historically associated with the ancestors of U.S. President George Washington.
- 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_69e11e46c0188190800181a4233f28fe |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1574bccb08190a6236dd14cf0fc5b |
completed | April 29, 2026, 12:56 a.m. |
Created at: April 16, 2026, 8:41 p.m.