Triple
T38673242
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crystal Beach |
E943657
|
entity |
| Predicate | oppositeAcrossLakeFrom |
P64456
|
FINISHED |
| Object | Buffalo, New York |
—
|
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: Buffalo, New York | Statement: [Crystal Beach, oppositeAcrossLakeFrom, Buffalo, New York]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oppositeAcrossLakeFrom Context triple: [Crystal Beach, oppositeAcrossLakeFrom, Buffalo, New York]
-
A.
locatedAcrossRiverFrom
Indicates that one entity is situated on the opposite side of a river relative to another entity.
-
B.
oppositeShoreFrom
Indicates that two locations are situated on facing sides of the same body of water or shoreline, directly across from each other.
-
C.
acrossWaterFrom
chosen
Indicates that two entities are located on opposite sides of a body of water, separated by that water.
-
D.
acrossLagoonFrom
Indicates that one entity is located on the opposite side of a lagoon relative to another entity.
-
E.
bodyOfWaterOnOtherSide
Indicates that one entity is located across a body of water from the other entity, with the water lying between them.
- F. None of above.
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_69f76eec28708190b9c82a505fc278e0 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fdec5ffe088190ac5505f26c6cff18 |
completed | May 8, 2026, 2 p.m. |
| PD | Predicate disambiguation | batch_69fdeae15f1c81908fc63fbc1b028d2e |
completed | May 8, 2026, 1:53 p.m. |
Created at: May 3, 2026, 4:33 p.m.