Triple
T33192356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | L’Écume des jours |
E849642
|
entity |
| Predicate | containsCharacterObsession |
P49999
|
FINISHED |
| Object | Jean-Sol Partre |
—
|
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: Jean-Sol Partre | Statement: [L’Écume des jours, containsCharacterObsession, Jean-Sol Partre]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: containsCharacterObsession Context triple: [L’Écume des jours, containsCharacterObsession, Jean-Sol Partre]
-
A.
obsessionWith
chosen
Indicates an intense, persistent, and often overwhelming preoccupation or fixation that one entity has toward another entity or object.
-
B.
characterReveals
Indicates that one character discloses or makes known information, feelings, or intentions to another character.
-
C.
hasFetish
Indicates a relationship where one entity has a strong sexual fixation, attraction, or arousal specifically focused on another entity or on a particular object, body part, or activity.
-
D.
hasEnigmaticCharacter
Indicates that something possesses a mysterious, puzzling, or difficult-to-interpret quality or nature.
-
E.
allyOfCharacter
Indicates that one character maintains an alliance or supportive partnership with another character.
- 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_69f3495e0f108190a6a7006f79f9c2c3 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a00119d821c8190874786391b27ef23 |
completed | May 10, 2026, 5:03 a.m. |
| PD | Predicate disambiguation | batch_6a001143fb6881909ac0ae8bfea04351 |
completed | May 10, 2026, 5:01 a.m. |
Created at: May 1, 2026, 1:29 a.m.