Triple
T33728308
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salome Otterbourne |
E864204
|
entity |
| Predicate | knowsCharacter |
P177250
|
FINISHED |
| Object | Hercule Poirot |
—
|
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: Hercule Poirot | Statement: [Salome Otterbourne, knowsCharacter, Hercule Poirot]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: knowsCharacter Context triple: [Salome Otterbourne, knowsCharacter, Hercule Poirot]
-
A.
refersToCharacter
Indicates that one entity makes reference to, mentions, or points to a specific character as its subject.
-
B.
notableCharacterName
Indicates that the subject has a notable or significant character whose name is given by the object.
-
C.
franchiseCharacter
Indicates a relationship where a character belongs to, appears in, or is part of a particular media franchise.
-
D.
meetsFictionalCharacter
Indicates that one entity encounters or comes into contact with a fictional character.
-
E.
associatedCharacters
Indicates that two or more characters are linked or connected through some relationship, involvement, or relevance to each other.
- 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_69f3498a64cc8190b4b414c67b280d93 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6fb1b91bc8190a40733039fe939b3 |
completed | May 3, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69f6f96dd4c8819093d6a7bd046a9ad5 |
completed | May 3, 2026, 7:29 a.m. |
| PDg | Predicate description generation | batch_69f6fa335b908190a20d92d5396203b5 |
completed | May 3, 2026, 7:33 a.m. |
Created at: May 1, 2026, 1:44 a.m.