Triple
T38593568
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dragonblade |
E932508
|
entity |
| Predicate | languageCallout |
P203868
|
FINISHED |
| Object | “Ryūjin no ken o kurae!” |
—
|
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: “Ryūjin no ken o kurae!” | Statement: [Dragonblade, languageCallout, “Ryūjin no ken o kurae!”]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageCallout Context triple: [Dragonblade, languageCallout, “Ryūjin no ken o kurae!”]
-
A.
communicationFunction
Indicates that one entity serves a communicative role or purpose in relation to another, such as conveying, mediating, or facilitating the exchange of information.
-
B.
communicationService
Indicates a relationship where one entity provides or facilitates a means for another entity to exchange information or messages.
-
C.
displayCall
Indicates that one entity presents or shows a call (such as a phone call or function call) to another entity or to a user interface.
-
D.
phoneCallContent
Indicates that one entity is the subject or content of a phone call made between two or more entities.
-
E.
callType
Indicates the category or nature of a call (such as its purpose, direction, or handling), distinguishing one kind of call from another.
- F. None of above. chosen
Provenance (4 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a0227ce59a081909fe1ba1181d86b4d |
completed | May 11, 2026, 7:02 p.m. |
| PD | Predicate disambiguation | batch_6a02273989208190beb948b8c7bdaee3 |
completed | May 11, 2026, 7 p.m. |
| PDg | Predicate description generation | batch_6a0227cd6e348190983e90e349aa155b |
completed | May 11, 2026, 7:02 p.m. |
Created at: May 3, 2026, 4:32 p.m.