Triple
T19386115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blue Eye spring |
E484937
|
entity |
| Predicate | shapeAssociation |
P136254
|
FINISHED |
| Object | eye-like appearance |
—
|
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: eye-like appearance | Statement: [Blue Eye spring, shapeAssociation, eye-like appearance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shapeAssociation Context triple: [Blue Eye spring, shapeAssociation, eye-like appearance]
-
A.
elementalAssociation
Indicates an association where one entity is linked or related to a particular element or elemental property (such as fire, water, earth, or air).
-
B.
antAssociation
Indicates a relationship in which one entity is associated or interacts in a specific, notable way with ants.
-
C.
alignmentRelation
Indicates that one entity is positioned, oriented, or arranged in a specific way relative to another entity.
-
D.
facesAssociatedWith
Indicates that there is a connection or linkage between certain faces (e.g., facial instances or representations) and related entities, contexts, or records.
-
E.
alignmentShape
Indicates that one entity’s shape is arranged, oriented, or matched in position relative to another entity’s shape.
- 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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61b40d1148190b4fcd9ad56aa6910 |
completed | April 20, 2026, 12:25 p.m. |
| PD | Predicate disambiguation | batch_69e4fd602f008190aa9bc76ae17e4ce1 |
completed | April 19, 2026, 4:05 p.m. |
| PDg | Predicate description generation | batch_69e50213571881909cd7543a43b51986 |
completed | April 19, 2026, 4:25 p.m. |
Created at: April 10, 2026, 1:35 p.m.