Triple
T6588968
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oakwood |
E159299
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Great Kills |
E146141
|
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: Great Kills | Statement: [Oakwood, adjacentTo, Great Kills]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Great Kills Context triple: [Oakwood, adjacentTo, Great Kills]
-
A.
Great Kills
chosen
Great Kills is a residential neighborhood on Staten Island’s South Shore known for its marina, waterfront parks, and suburban character.
-
B.
Killers
Killers is Iron Maiden’s second studio album, known for its raw, aggressive sound and for solidifying the band’s early heavy metal style.
-
C.
Shoot to Kill
Shoot to Kill is a 1988 American thriller film about an FBI agent and a mountain guide tracking a murderous criminal through the wilderness.
-
D.
Murder City
"Murder City" is a punk rock song by Green Day from their politically charged concept album *21st Century Breakdown*.
-
E.
Killing Times
The Killing Times were a period of brutal persecution and summary executions of Scottish Covenanters in the late 17th century under the Stuart monarchy.
- 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_69c688366ce8819083f8883983c0df92 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6aeb0e9d88190aa861e742ff6804e |
completed | March 27, 2026, 4:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6d5794f388190a04f4f9c9e628f22 |
completed | March 27, 2026, 7:07 p.m. |
Created at: March 27, 2026, 1:55 p.m.