Triple
T18324144
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Daken |
E438958
|
entity |
| Predicate | clawsCoating |
P81140
|
FINISHED |
| Object | Muramasa metal on one claw |
—
|
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: Muramasa metal on one claw | Statement: [Daken, clawsCoating, Muramasa metal on one claw]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: clawsCoating Context triple: [Daken, clawsCoating, Muramasa metal on one claw]
-
A.
skeletonCoating
Indicates that one entity serves as a coating, covering, or outer layer on the skeleton of another entity.
-
B.
coatingType
chosen
Indicates the type or kind of coating applied to or associated with an entity.
-
C.
clawDescription
Indicates that one entity provides a descriptive account or characterization of a claw or claw-like feature of another entity.
-
D.
hasClaws
Indicates that one entity possesses claws as a physical feature or attribute.
-
E.
clawsAdaptedFor
Indicates that an organism’s claws are specially suited or modified for a particular function, environment, or behavior.
- 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_69d8b916a2d081909e249e4902f6aad9 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50aa93fb0819083293b80e8400c4e |
completed | April 19, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69e44fe4ee10819086b4142444fca1f5 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:36 a.m.