Triple
T25090822
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rocamadour cheese |
E628449
|
entity |
| Predicate | surfaceMold |
P47694
|
FINISHED |
| Object | can develop thin white mold with age |
—
|
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: can develop thin white mold with age | Statement: [Rocamadour cheese, surfaceMold, can develop thin white mold with age]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: surfaceMold Context triple: [Rocamadour cheese, surfaceMold, can develop thin white mold with age]
-
A.
surfaceType
Indicates the kind or classification of surface associated with an entity or interaction.
-
B.
surfaceExpressionOf
Indicates that one entity is a specific surface-level manifestation or observable form of another underlying entity or concept.
-
C.
surfaceFormedBy
Indicates that a surface is created, shaped, or defined as a result of a particular process, interaction, or set of contributing factors.
-
D.
surfaceFeatureOf
chosen
Indicates that one entity is a surface-level characteristic, pattern, or feature belonging to or present on another entity.
-
E.
surfaceBehavior
Indicates how an entity behaves or interacts specifically at or on its surface.
- 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_69e2ff2f58e881908340527bc5d34f07 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f497bc12b881908fe3386c66252bf6 |
completed | May 1, 2026, 12:08 p.m. |
| PD | Predicate disambiguation | batch_69f49366e8d08190adb4b71fe3a14683 |
completed | May 1, 2026, 11:49 a.m. |
Created at: April 18, 2026, 6:24 a.m.