Triple
T9131173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dora Milaje |
E219087
|
entity |
| Predicate | roleInWakanda |
P87290
|
FINISHED |
| Object | protect the king |
—
|
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: protect the king | Statement: [Dora Milaje, roleInWakanda, protect the king]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInWakanda Context triple: [Dora Milaje, roleInWakanda, protect the king]
-
A.
roleInWakandaForever
Indicates that an entity had a role or participation in the production of the film "Black Panther: Wakanda Forever."
-
B.
roleInEndgame
Indicates that an entity has a specific function, position, or responsibility within the final or concluding phase of an event, process, or scenario.
-
C.
roleInWZRD
Indicates that an entity holds a specific role or function within the context of WZRD.
-
D.
isMostPowerfulFigureIn
Indicates that the subject holds the greatest level of power, authority, or influence within the specified group, organization, or context.
-
E.
roleOfWillChampion
Indicates that one entity is the specific role, position, or function held by Will Champion in relation to another entity.
- 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_69ca83debfc0819095800583e97ab10f |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca8ceea6c81909f368f12dac1649c |
completed | April 1, 2026, 5:10 a.m. |
| PD | Predicate disambiguation | batch_69cc6601d77881908299d58db6e64937 |
completed | April 1, 2026, 12:25 a.m. |
| PDg | Predicate description generation | batch_69cc6a3c78388190a7436acc0e44ff55 |
completed | April 1, 2026, 12:43 a.m. |
Created at: March 30, 2026, 7:18 p.m.