Triple
T17138122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gisk’aast (Killer Whale) |
E415891
|
entity |
| Predicate | usesVisualEmblem |
P29556
|
FINISHED |
| Object | killer whale crest |
—
|
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: killer whale crest | Statement: [Gisk’aast (Killer Whale), usesVisualEmblem, killer whale crest]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesVisualEmblem Context triple: [Gisk’aast (Killer Whale), usesVisualEmblem, killer whale crest]
-
A.
emblemUsedBy
chosen
Indicates that a particular emblem is adopted or employed by a specific entity as its symbol or identifying mark.
-
B.
containsEmblem
Indicates that one entity includes or displays the emblem of another entity as part of its design or composition.
-
C.
emblemName
Indicates that a specified name is the official or recognized title of an emblem.
-
D.
protectiveEmblemName
Indicates that a given name is the designated title or label of a protective emblem associated with an entity or context.
-
E.
hasEmblemColor
Indicates that an emblem possesses or is characterized by a specific color.
- 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_69d886d15af4819092f92f8a129763e6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f2d1277881909325ffd2a7aa4873 |
completed | April 18, 2026, 9:08 p.m. |
| PD | Predicate disambiguation | batch_69e3830192ac819091344a9e5a36c8c9 |
completed | April 18, 2026, 1:11 p.m. |
Created at: April 10, 2026, 5:36 a.m.