Triple
T28776699
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mrs Norris |
E726551
|
entity |
| Predicate | treatsUnkindly |
P20070
|
FINISHED |
| Object | Fanny Price |
—
|
NE NERFINISHED |
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: Fanny Price | Statement: [Mrs Norris, treatsUnkindly, Fanny Price]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: treatsUnkindly Context triple: [Mrs Norris, treatsUnkindly, Fanny Price]
-
A.
treatsHumansAs
Indicates how one entity regards or behaves toward humans, characterizing them in a particular way (e.g., as equals, tools, resources, or threats).
-
B.
treatmentOf
Indicates a relationship where one entity administers, provides, or is responsible for a therapeutic intervention directed toward another entity (typically a patient or condition).
-
C.
treatsHumanely
Indicates that one entity interacts with or cares for another in a way that respects their well-being, dignity, and humane treatment.
-
D.
persecutes
chosen
Indicates that one entity persistently harasses, oppresses, or inflicts suffering on another, often in an unjust or hostile manner.
-
E.
treats
Indicates that one entity provides medical care or therapeutic intervention to another entity.
- 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_69f03199997c8190b6ae43fb19312443 |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f676f968d08190a4adba0439b438c9 |
completed | May 2, 2026, 10:13 p.m. |
| PD | Predicate disambiguation | batch_69f675ff62c48190a634bbb8896973b9 |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 28, 2026, 6:18 a.m.