Triple
T23634092
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sapphire |
E583692
|
entity |
| Predicate | differsFromRubyBy |
P61682
|
FINISHED |
| Object | color definition within corundum group |
—
|
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: color definition within corundum group | Statement: [Sapphire, differsFromRubyBy, color definition within corundum group]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: differsFromRubyBy Context triple: [Sapphire, differsFromRubyBy, color definition within corundum group]
-
A.
isInterpretedDifferentlyIn
Indicates that the same item, event, or expression is understood or construed in a different way within a specified context, group, or setting.
-
B.
differIn
chosen
Indicates that two entities are not the same in at least one specified aspect, attribute, or value.
-
C.
mayDifferFrom
Indicates that one entity is allowed or expected to be different from another entity, without requiring them to be identical.
-
D.
isDistinctFrom
Indicates that two entities are not identical and can be clearly distinguished from one another.
-
E.
hasLexicalDifferencesWith
Indicates that two linguistic items differ from each other in their word choice or lexical form.
- 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_69e248fe1c2c8190ac914d2442ff3d26 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b1eb38a481909f7ceeaefb7b43ce |
completed | April 29, 2026, 7:23 a.m. |
| PD | Predicate disambiguation | batch_69f118d0e0588190a86527a7747c5427 |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:47 p.m.