Triple
T13195262
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Claire Tow Theater |
E314094
|
entity |
| Predicate | roofLocation |
P108989
|
FINISHED |
| Object | on the roof of the Vivian Beaumont Theater building |
—
|
LITERAL 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: on the roof of the Vivian Beaumont Theater building | Statement: [Claire Tow Theater, roofLocation, on the roof of the Vivian Beaumont Theater building]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roofLocation Context triple: [Claire Tow Theater, roofLocation, on the roof of the Vivian Beaumont Theater building]
-
A.
doorLocation
Indicates the spatial position or placement of a door relative to a reference structure or area.
-
B.
roofLevel
Indicates the vertical level or story of a building at which the roof is located or begins.
-
C.
roofFeature
Indicates that one entity is a feature, element, or characteristic that is part of or associated with a roof.
-
D.
locationOfStructure
Indicates that a particular structure is situated at or occupies a specific location.
-
E.
roofHeight
Indicates the vertical distance or elevation of a roof relative to a reference level or structure.
- F. None of above. chosen
Provenance (4 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_69d806ae1e08819090d95bfe1538cc17 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98cf054f88190b05ced98d5a22a62 |
completed | April 10, 2026, 11:51 p.m. |
| PD | Predicate disambiguation | batch_69d98bc6bc108190b5a6a265bf6e9fd4 |
completed | April 10, 2026, 11:46 p.m. |
| PDg | Predicate description generation | batch_69d98ceeb22c8190a6be666031d9e5a4 |
completed | April 10, 2026, 11:51 p.m. |
Created at: April 9, 2026, 9:16 p.m.