Triple
T8245790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DuPont Tedlar |
E192844
|
entity |
| Predicate | surfaceFunction |
P14798
|
FINISHED |
| Object | protect underlying substrates |
—
|
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: protect underlying substrates | Statement: [DuPont Tedlar, surfaceFunction, protect underlying substrates]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: surfaceFunction Context triple: [DuPont Tedlar, surfaceFunction, protect underlying substrates]
-
A.
surfaceFeatureOf
Indicates that one entity is a surface-level characteristic, pattern, or feature belonging to or present on another entity.
-
B.
surfaceType
Indicates the kind or classification of surface associated with an entity or interaction.
-
C.
surfaceExpressionOf
Indicates that one entity is a specific surface-level manifestation or observable form of another underlying entity or concept.
-
D.
surfaceBehavior
chosen
Indicates how an entity behaves or interacts specifically at or on its surface.
-
E.
surfaceOperation
Indicates an operation or activity that is performed on or at the surface of an object, material, or environment.
- 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_69ca82de7b8c81908d8106f8a53cff9b |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb7872f6d481909ea1d3c2aad1a2b1 |
completed | March 31, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69cb36b437e881909958591357e83b9d |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:48 p.m.