Triple
T9230073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | the Creature |
E221792
|
entity |
| Predicate | requestsFrom |
P34717
|
FINISHED |
| Object | a female companion |
—
|
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: a female companion | Statement: [the Creature, requestsFrom, a female companion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requestsFrom Context triple: [the Creature, requestsFrom, a female companion]
-
A.
requestedFrom
chosen
Indicates that one entity has made a request to another entity as the source or provider of something.
-
B.
requestedBy
Indicates that one entity has made a request for something to be done, provided, or obtained by another entity.
-
C.
requestType
Indicates the specific kind or category of request being made in an interaction or transaction.
-
D.
requestModel
Indicates that one entity asks another entity to provide or use a specific model for a task or interaction.
-
E.
requestsCooperationWith
Indicates that one entity asks another entity to collaborate or assist in achieving a task, goal, or outcome.
- 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_69ca83ed628c8190bc02d641e57f097f |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccee17a2dc8190b373f78be7247f0d |
completed | April 1, 2026, 10:06 a.m. |
| PD | Predicate disambiguation | batch_69cc7a3daeb481908b0abde3fbc1f1f0 |
completed | April 1, 2026, 1:51 a.m. |
Created at: March 30, 2026, 7:29 p.m.