Triple
T5672643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Giza core limestone |
E125012
|
entity |
| Predicate | outerAppearance |
P311
|
FINISHED |
| Object | not used for fine outer casing |
—
|
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: not used for fine outer casing | Statement: [Giza core limestone, outerAppearance, not used for fine outer casing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: outerAppearance Context triple: [Giza core limestone, outerAppearance, not used for fine outer casing]
-
A.
outerSurface
Indicates that one entity forms the external boundary or outermost layer of another entity.
-
B.
appearance
chosen
Indicates how something looks or seems to an observer, including its visible form, condition, or outward impression.
-
C.
returnAppearance
Indicates that one entity resumes or restores a previous visual form, style, or outward appearance of another entity or of itself.
-
D.
typicalAppearanceContext
Indicates the usual situation, setting, or context in which an entity most commonly appears or is typically encountered.
-
E.
adaptationAppearance
Indicates that one entity appears or is depicted in an adaptation of another entity (such as a work being represented in a derived or reinterpreted version).
- 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_69c008295c808190acfe78915e7d656a |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c025303860819093e51f176babed71 |
completed | March 22, 2026, 5:21 p.m. |
| PD | Predicate disambiguation | batch_69c021bc3894819084f37d14ba4b2644 |
completed | March 22, 2026, 5:07 p.m. |
Created at: March 22, 2026, 3:43 p.m.