Triple
T1156876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yale University’s Beinecke Plaza |
E24401
|
entity |
| Predicate | hasSurfaceMaterial |
P1845
|
FINISHED |
| Object | stone paving |
—
|
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: stone paving | Statement: [Yale University’s Beinecke Plaza, hasSurfaceMaterial, stone paving]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSurfaceMaterial Context triple: [Yale University’s Beinecke Plaza, hasSurfaceMaterial, stone paving]
-
A.
hasMaterialType
chosen
Indicates that something is composed of, made from, or characterized by a specific type of material.
-
B.
surfaceType
Indicates the kind or classification of surface associated with an entity or interaction.
-
C.
materialUsed
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
D.
material
Indicates that one entity is physically composed of, made from, or constructed using the substance or material represented by the other entity.
-
E.
hasFloorMaterial
Indicates that an entity’s floor is made of, covered with, or constructed from a specified material.
- 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_69a494060e148190abb42f971242c197 |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bc92ae008190a587c12ecc9a502a |
completed | March 1, 2026, 10:24 p.m. |
| PD | Predicate disambiguation | batch_69a4bb50d19c81908a98dbbb04a8906f |
completed | March 1, 2026, 10:18 p.m. |
Created at: March 1, 2026, 7:44 p.m.