Triple
T33855565
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gladys Mitchell |
E867762
|
entity |
| Predicate | Mrs. BradleyCharacterDescription |
P32702
|
FINISHED |
| Object | eccentric psychoanalyst detective |
—
|
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: eccentric psychoanalyst detective | Statement: [Gladys Mitchell, Mrs. BradleyCharacterDescription, eccentric psychoanalyst detective]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Mrs. BradleyCharacterDescription Context triple: [Gladys Mitchell, Mrs. BradleyCharacterDescription, eccentric psychoanalyst detective]
-
A.
characterDescription
chosen
Indicates that one entity provides a textual description or portrayal of the characteristics, traits, or attributes of another entity.
-
B.
describedAsByBertieWooster
Indicates that something is characterized or portrayed in a particular way by the character Bertie Wooster.
-
C.
belovedCharacter
Indicates that one entity is a character who is deeply loved, cherished, or held in special affection by another entity.
-
D.
characterRoleOfJeeves
Indicates that the subject is the narrative or fictional role played by the character Jeeves.
-
E.
roleOfVernonHandley
Indicates that the specified role or position is held or performed by Vernon Handley.
- 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_69f349943ccc8190a3c41a3e0ae46cbf |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f70077947c81908ad28b9185094cf4 |
completed | May 3, 2026, 7:59 a.m. |
| PD | Predicate disambiguation | batch_69f6fc59518081908b0275f47721d561 |
completed | May 3, 2026, 7:42 a.m. |
Created at: May 1, 2026, 1:47 a.m.