Triple
T26928584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adèle Varens |
E678150
|
entity |
| Predicate | guardianRelationship |
P75214
|
FINISHED |
| Object | Rochester denies certain paternity |
—
|
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: Rochester denies certain paternity | Statement: [Adèle Varens, guardianRelationship, Rochester denies certain paternity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: guardianRelationship Context triple: [Adèle Varens, guardianRelationship, Rochester denies certain paternity]
-
A.
protectiveRelationshipWith
Indicates a relationship in which one entity actively safeguards, defends, or looks out for the well-being of another.
-
B.
parentRelationship
chosen
Indicates a familial relationship in which one entity is the parent of another entity.
-
C.
basisOfRelationship
Indicates that one entity serves as the foundational reason, cause, or justification for the relationship that exists between two or more entities.
-
D.
relationshipToParents
Indicates the type or nature of a person's familial relationship to their parents.
-
E.
establishedRelationship
Indicates that a formal, recognized relationship has been created and is now in effect between the referenced entities.
- 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_69eeeb4cac908190a45956c2993d1cc2 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f62013a6348190bd1b5a8eed5c3e82 |
completed | May 2, 2026, 4:02 p.m. |
| PD | Predicate disambiguation | batch_69f61b3d23f481908dfec27adace900a |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 6:11 a.m.