Triple
T24226324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ondine (film) |
E601605
|
entity |
| Predicate | hasChildCharacterWithCondition |
P5716
|
FINISHED |
| Object | Annie has kidney disease |
—
|
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: Annie has kidney disease | Statement: [Ondine (film), hasChildCharacterWithCondition, Annie has kidney disease]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasChildCharacterWithCondition Context triple: [Ondine (film), hasChildCharacterWithCondition, Annie has kidney disease]
-
A.
hasChildCharacters
Indicates that one entity includes or is associated with other entities that are considered its child characters in a hierarchical or narrative structure.
-
B.
hasChildrenWith
Indicates that two entities share one or more biological or adopted children together.
-
C.
leadCharacterHasChild
Indicates that the lead character is the parent of the specified child.
-
D.
hasSiblingCharacters
Indicates that two characters share at least one common parent, making them siblings in the narrative or data context.
-
E.
containsCharacter
chosen
Indicates that one entity includes a specific character as part of its content or composition.
- 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_69e29537ca548190b94a37ebe1977caf |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f287dffa6c81908564b74dbfae780b |
completed | April 29, 2026, 10:36 p.m. |
| PD | Predicate disambiguation | batch_69f1c448abec8190b87cbf9ed419a309 |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 18, 2026, midnight