Triple
T20162737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salisbury Park trails |
E491752
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Salisbury Park |
—
|
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: Salisbury Park | Statement: [Salisbury Park trails, locatedIn, Salisbury Park]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Salisbury Park Context triple: [Salisbury Park trails, locatedIn, Salisbury Park]
-
A.
Salisbury Park
chosen
Salisbury Park is a public park in Worcester, Massachusetts, best known as the hilltop site of the historic stone Bancroft Tower.
-
B.
Salisbury Park
Salisbury Park is a residential suburb in the northern Adelaide metropolitan area of South Australia.
-
C.
Sutcliffe Park
Sutcliffe Park is a public green space in the Kidbrooke area of southeast London, featuring open lawns, sports facilities, and nature conservation areas.
-
D.
Courtland Park
Courtland Park is a public recreational park located in Reidsville, North Carolina.
-
E.
Howden Park
Howden Park is a public recreational area in the Howden district, typically offering green space, walking paths, and community leisure facilities.
- 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_69da6266c6888190bc1a3ecf24814d34 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e667e505888190a05e26a3c5a0ede1 |
completed | April 20, 2026, 5:52 p.m. |
Created at: April 11, 2026, 11:34 p.m.