Triple
T32268820
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Park Row Building |
E824361
|
entity |
| Predicate | hasTwinCupolas |
P53361
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Park Row Building, hasTwinCupolas, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTwinCupolas Context triple: [Park Row Building, hasTwinCupolas, true]
-
A.
hasTwinCaissons
Indicates that something is equipped with or associated with a pair of caissons functioning together as twins.
-
B.
hasTwinStructureWith
Indicates that two entities share an identical or nearly identical structural form, typically as corresponding or mirrored counterparts.
-
C.
hasTwinSystemWith
Indicates that two systems are twins, meaning they are closely paired or mirrored counterparts in structure, function, or configuration.
-
D.
hasTwinFeature
chosen
Indicates that two entities share an identical or nearly identical feature, characteristic, or component, as if they are twins in that respect.
-
E.
hasArchitecturalTwin
Indicates that two entities share nearly identical architectural design, form, or structure, effectively making them architectural counterparts or duplicates.
- 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_69f3490e73588190915f282edd105772 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6bc858f288190a674b92fac98b600 |
completed | May 3, 2026, 3:09 a.m. |
| PD | Predicate disambiguation | batch_69f6b632cf788190a3d0c08cd026b84b |
completed | May 3, 2026, 2:42 a.m. |
Created at: May 1, 2026, 12:42 a.m.