Triple
T27538655
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. Steel Building (informal, historical) |
E695167
|
entity |
| Predicate | refersToFacadeMaterial |
P19176
|
FINISHED |
| Object | black steel |
—
|
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: black steel | Statement: [U.S. Steel Building (informal, historical), refersToFacadeMaterial, black steel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refersToFacadeMaterial Context triple: [U.S. Steel Building (informal, historical), refersToFacadeMaterial, black steel]
-
A.
featuresMaterialType
Indicates that an entity is characterized by or incorporates a specific type of material.
-
B.
featuresMaterialFrom
Indicates that one entity incorporates, contains, or is composed of material originating from another entity.
-
C.
testedMaterial
Indicates that an entity has been used as the material or substance on which a test or experiment was performed.
-
D.
facadeFeature
Indicates that one element functions as a distinct architectural or design feature on the façade of another structure.
-
E.
exteriorMaterial
chosen
Indicates the material that forms the outer surface or outer construction of an object or structure.
- 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_69ef538608b081908b9f659bb09d5e0f |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f7221dc9a88190bb8194fcc29c42bc |
completed | May 3, 2026, 10:23 a.m. |
| PD | Predicate disambiguation | batch_69f72153a9188190b02adc84e1be4af8 |
completed | May 3, 2026, 10:20 a.m. |
Created at: April 27, 2026, 1:29 p.m.