Triple
T20129765
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kanka |
E490856
|
entity |
| Predicate | incognitoRole |
P92521
|
FINISHED |
| Object | courtier in the court of King Virata |
—
|
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: courtier in the court of King Virata | Statement: [Kanka, incognitoRole, courtier in the court of King Virata]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: incognitoRole Context triple: [Kanka, incognitoRole, courtier in the court of King Virata]
-
A.
secretRole
Indicates that an entity holds a role or function that is intentionally hidden or not publicly disclosed within a given context.
-
B.
covertRole
chosen
Indicates that an entity holds or performs a hidden, secret, or undercover role in relation to another entity or context.
-
C.
exportRole
Indicates that an entity functions in a capacity or role specifically related to exporting goods, services, or data.
-
D.
gammaRole
Indicates a tertiary or supporting role that an entity plays within a structured hierarchy of roles or participants in an event or relationship.
-
E.
ClientRole
Indicates that an entity participates in a relationship or interaction specifically in the capacity of a client.
- 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_69da62651a0c8190a3e05e95e056a66b |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e66760b8f08190a66fbb2e9e3925a3 |
completed | April 20, 2026, 5:50 p.m. |
| PD | Predicate disambiguation | batch_69e54cfb0d0081908e789b9b57e96668 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 11:31 p.m.