Triple
T13153988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | East Tāmaki |
E312535
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Flat Bush |
E297542
|
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: Flat Bush | Statement: [East Tāmaki, near, Flat Bush]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Flat Bush Context triple: [East Tāmaki, near, Flat Bush]
-
A.
Flat Bush
chosen
Flat Bush is a rapidly growing residential suburb in southeast Auckland, New Zealand, known for its planned urban development and diverse community.
-
B.
Forest Hills
Forest Hills is a primarily residential neighborhood in central Queens, New York City, known for its tree-lined streets, Tudor-style homes, and the historic Forest Hills Stadium.
-
C.
Forest Hills
Forest Hills is a residential neighborhood in northwest Washington, D.C., known for its leafy streets, embassies, and proximity to Rock Creek Park and the Van Ness commercial corridor.
-
D.
Forest Hills
Forest Hills is a major transit hub and neighborhood in Boston, Massachusetts, serving as a key terminus for multiple commuter rail, subway, and bus lines.
-
E.
Forest Hills
Forest Hills is a residential neighbourhood within the community of Cole Harbour in Nova Scotia, Canada.
- 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_69d806aabde48190899e13e41659cae5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98c06ccb881909390df18e1a6f7ed |
completed | April 10, 2026, 11:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6eaee8aa0819089994b85d56c7740 |
completed | May 3, 2026, 6:27 a.m. |
Created at: April 9, 2026, 9:11 p.m.