Triple
T32078012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mor'du |
E819210
|
entity |
| Predicate | roleInBackstory |
P119461
|
FINISHED |
| Object | legendary demon bear |
—
|
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: legendary demon bear | Statement: [Mor'du, roleInBackstory, legendary demon bear]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInBackstory Context triple: [Mor'du, roleInBackstory, legendary demon bear]
-
A.
roleInCharacterBackstory
chosen
Indicates that one entity plays a specific role or part in shaping another entity’s character backstory or personal history.
-
B.
roleOfCharacter
Indicates that one entity serves as the narrative or functional role played by a character within a story, scenario, or context.
-
C.
roleInStories
Indicates the specific function, position, or character part an entity plays within one or more stories.
-
D.
roleInDialogue
Indicates that an entity participates in a dialogue with a specific conversational role (e.g., speaker, listener, moderator) relative to other participants.
-
E.
roleForProtagonist
Indicates the specific narrative or functional role that an entity plays in relation to the story’s main protagonist.
- 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_69f348ff8ef88190931c08ba530a36bc |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a00053d8004819097ad9cf6431a20a3 |
completed | May 10, 2026, 4:10 a.m. |
| PD | Predicate disambiguation | batch_6a0004b3a82c81908e2bf9a533a93eb6 |
completed | May 10, 2026, 4:08 a.m. |
Created at: May 1, 2026, 12:24 a.m.