Triple
T37665163
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Purpur Block |
E937803
|
entity |
| Predicate | materialFamily |
P189776
|
FINISHED |
| Object | Purpur |
—
|
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: Purpur | Statement: [Purpur Block, materialFamily, Purpur]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: materialFamily Context triple: [Purpur Block, materialFamily, Purpur]
-
A.
material
Indicates that one entity is physically composed of, made from, or constructed using the substance or material represented by the other entity.
-
B.
materialCharacteristics
Indicates the inherent physical or compositional properties that define a material’s behavior or performance in a given context.
-
C.
materialVariant
Indicates that one entity is a version or variation of another entity distinguished by differences in material composition.
-
D.
featuresMaterialType
Indicates that an entity is characterized by or incorporates a specific type of material.
-
E.
materialOptions
Indicates that there are one or more possible materials that can be chosen or applied in relation to a given entity or context.
- F. None of above. chosen
Provenance (4 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_69f76ed6df7c8190b018e5baea716ceb |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbca6c066c8190a1599202f341417f |
completed | May 6, 2026, 11:10 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ec03ac8190a757563f96fab283 |
completed | May 6, 2026, 11:04 p.m. |
| PDg | Predicate description generation | batch_69fbc9d0854c8190aa00093274afebb8 |
completed | May 6, 2026, 11:08 p.m. |
Created at: May 3, 2026, 4:18 p.m.