Triple
T23634025
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sapphire |
E583692
|
entity |
| Predicate | isSecondOnlyInHardnessTo |
P9524
|
FINISHED |
| Object | diamond |
—
|
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: diamond | Statement: [Sapphire, isSecondOnlyInHardnessTo, diamond]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isSecondOnlyInHardnessTo Context triple: [Sapphire, isSecondOnlyInHardnessTo, diamond]
-
A.
secondOnlyTo
chosen
Indicates that one entity ranks immediately below another in degree, importance, or quality, with only that other entity surpassing it.
-
B.
showsHardnessOf
Indicates that something displays or reveals the degree of hardness possessed by another entity.
-
C.
isSecondHighest
Indicates that one entity ranks immediately below the highest-ranked entity within a specified ordering or set.
-
D.
hardness
Indicates the degree to which one entity resists being scratched, indented, or deformed by another.
-
E.
impliesHardness
Indicates that one entity suggests, entails, or leads to the conclusion that another entity possesses hardness.
- 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_69f1b1ea269c8190a677e812d7471a98 |
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.