Triple
T38616997
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 460 Park Avenue |
E936752
|
entity |
| Predicate | hasBuildingCategory |
P111268
|
FINISHED |
| Object | Class A or Class B office (Manhattan market classification) |
—
|
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: Class A or Class B office (Manhattan market classification) | Statement: [460 Park Avenue, hasBuildingCategory, Class A or Class B office (Manhattan market classification)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBuildingCategory Context triple: [460 Park Avenue, hasBuildingCategory, Class A or Class B office (Manhattan market classification)]
-
A.
hasBuildingClass
chosen
Indicates that a building is categorized as belonging to a specific building class or type.
-
B.
containsBuildingType
Indicates that a location or area includes at least one building of the specified type.
-
C.
listedBuildingCategory
Indicates the heritage protection grade or category assigned to a building that is officially recognized as a listed structure.
-
D.
containsBuilding
Indicates that one location or area includes a building within its boundaries.
-
E.
hasBuildingGrade
Indicates that a building is assigned a particular grade or quality rating.
- 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_69f76ed403208190b862dc795171353f |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd64bc86848190a49f451a8fc5cf1e |
completed | May 8, 2026, 4:21 a.m. |
| PD | Predicate disambiguation | batch_69fd5ff4a648819090756d90fd195d9a |
completed | May 8, 2026, 4 a.m. |
Created at: May 3, 2026, 4:32 p.m.