Triple
T30036093
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chlorastrolite |
E763160
|
entity |
| Predicate | valueFactor |
P4922
|
FINISHED |
| Object | sharpness of star pattern |
—
|
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: sharpness of star pattern | Statement: [Chlorastrolite, valueFactor, sharpness of star pattern]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: valueFactor Context triple: [Chlorastrolite, valueFactor, sharpness of star pattern]
-
A.
value
Indicates that one entity possesses, represents, or corresponds to a particular quantity, quality, or assigned worth.
-
B.
focusFactor
Indicates that one entity serves as a measure, component, or determinant of the degree of focus or concentration associated with another entity.
-
C.
considersFactor
chosen
Indicates that one entity takes another entity into account as a factor when forming a judgment, decision, or evaluation.
-
D.
valuedBy
Indicates that one entity is regarded as important, useful, or held in high esteem by another entity.
-
E.
valueSystem
Indicates that one entity embodies, adheres to, or is characterized by a particular set of values, principles, or evaluative standards defined 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_69f2246fb2b88190acff36bf7975c8f0 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6a916d2e08190bafc01cba73b6469 |
completed | May 3, 2026, 1:47 a.m. |
| PD | Predicate disambiguation | batch_69f6a7548eb48190a69b60a3c6ad53b9 |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 29, 2026, 6:51 p.m.