Triple
T9115934
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arkenstone of Thrain |
E218718
|
entity |
| Predicate | physicalAppearance |
P311
|
FINISHED |
| Object | brilliant white gem |
—
|
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: brilliant white gem | Statement: [Arkenstone of Thrain, physicalAppearance, brilliant white gem]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: physicalAppearance Context triple: [Arkenstone of Thrain, physicalAppearance, brilliant white gem]
-
A.
appearance
chosen
Indicates how something looks or seems to an observer, including its visible form, condition, or outward impression.
-
B.
physicalCharacteristics
Indicates that one entity has or describes the bodily or material attributes, features, or appearance of another entity.
-
C.
hasPhysicalFeature
Indicates that one entity possesses or exhibits a specific physical characteristic or feature of another entity.
-
D.
hasCharacterAppearance
Indicates that a character appears or is visually represented within a given work, scene, or context.
-
E.
characterMajorAppearance
Indicates that a character makes a significant or prominent appearance in a particular work or installment.
- 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_69ca83dc94ac8190b9ef42684d36ff39 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca8a1340881909dc791b825e87ef2 |
completed | April 1, 2026, 5:09 a.m. |
| PD | Predicate disambiguation | batch_69cc65fe5be081909d4470d6317b14a6 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:16 p.m.