Triple
T19920142
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Castle Shannon |
E478770
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Dormont |
—
|
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: Dormont | Statement: [Castle Shannon, adjacentTo, Dormont]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dormont Context triple: [Castle Shannon, adjacentTo, Dormont]
-
A.
Dormont
chosen
Dormont is a small residential borough in Allegheny County, Pennsylvania, located just southwest of Pittsburgh.
-
B.
Dunston
Dunston is the mischievous orangutan from the family comedy film "Dunston Checks In," known for causing chaos in a luxury hotel.
-
C.
Dunston
Dunston is a suburban district on the south bank of the River Tyne in Gateshead, England, known historically for its riverside industry and later redevelopment.
-
D.
Denniston
Denniston is a historic former coal-mining town on New Zealand’s rugged West Coast, known for its dramatic plateau setting and the famous Denniston Incline.
-
E.
Dunvant
Dunvant is a suburban village and community in the City and County of Swansea in south Wales.
- 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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e659c49d408190b3a42bada3675133 |
completed | April 20, 2026, 4:52 p.m. |
Created at: April 10, 2026, 1:53 p.m.