Triple
T37465031
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kronx Dragonhoof |
E931012
|
entity |
| Predicate | expansionKeyword |
P65488
|
FINISHED |
| Object | Invoke |
—
|
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: Invoke | Statement: [Kronx Dragonhoof, expansionKeyword, Invoke]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: expansionKeyword Context triple: [Kronx Dragonhoof, expansionKeyword, Invoke]
-
A.
expansionKeywordContext
Indicates the contextual relationship in which a keyword is expanded or interpreted, linking the keyword to the surrounding content or query intent.
-
B.
expands
Indicates that one entity increases in size, volume, scope, or extent relative to a previous state or another entity.
-
C.
definitionOfExpansion
Indicates that one entity specifies or explains the detailed meaning, scope, or elaboration of another entity’s expansion.
-
D.
associatedKeyword
chosen
Indicates that one entity is linked to or characterized by a particular keyword used for identification, categorization, or retrieval.
-
E.
expandsConcept
Indicates that one concept broadens, elaborates, or adds detail to the meaning or scope of another concept.
- 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_69f76ec1a1148190b0a961f188d621b0 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcef654d588190b29ecc76678d1aa0 |
completed | May 7, 2026, 8 p.m. |
| PD | Predicate disambiguation | batch_69fcecdb97f48190b382b7d13be92dc0 |
completed | May 7, 2026, 7:49 p.m. |
Created at: May 3, 2026, 4:17 p.m.