Triple
T34637999
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | T’nalak weaving |
E889481
|
entity |
| Predicate | patternSource |
P177497
|
FINISHED |
| Object | weavers’ dreams |
—
|
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: weavers’ dreams | Statement: [T’nalak weaving, patternSource, weavers’ dreams]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: patternSource Context triple: [T’nalak weaving, patternSource, weavers’ dreams]
-
A.
patternSourceType
chosen
Indicates the type or origin category of the pattern from which something is derived or generated.
-
B.
patternTableSource
Indicates that one entity serves as the source from which a pattern table or pattern-based data is derived or generated for another entity.
-
C.
patternSupport
Indicates that one entity provides evidence, validation, or reinforcement for the existence, correctness, or applicability of a particular pattern associated with another entity.
-
D.
pattern
Indicates that one entity exhibits, follows, or is characterized by a particular recurring form, structure, or arrangement associated with another entity.
-
E.
patternAppearance
Indicates that one entity exhibits, displays, or takes on the visual pattern or design characterized by another entity.
- 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_69f349d724848190b63ad3407e0006d9 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f7234bcaa48190ac970759d34e254a |
completed | May 3, 2026, 10:28 a.m. |
| PD | Predicate disambiguation | batch_69f72155c48881909bd40b9aa3febd5a |
completed | May 3, 2026, 10:20 a.m. |
Created at: May 1, 2026, 2:04 a.m.