Triple
T1379060
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brigitte Macron |
E29294
|
entity |
| Predicate | hasStepChild |
P25182
|
FINISHED |
| Object | Emmanuel Macron’s nieces and nephews |
—
|
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: Emmanuel Macron’s nieces and nephews | Statement: [Brigitte Macron, hasStepChild, Emmanuel Macron’s nieces and nephews]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStepChild Context triple: [Brigitte Macron, hasStepChild, Emmanuel Macron’s nieces and nephews]
-
A.
hasStepchildren
chosen
Indicates that one person has stepchildren, meaning children of their spouse or partner from a previous relationship.
-
B.
hasStep
Indicates that one entity includes, is composed of, or is associated with a specific step or stage in a process involving another entity.
-
C.
hasChildrenWith
Indicates that two entities share one or more biological or adopted children together.
-
D.
has child
Indicates that one entity is the parent of another entity, which is its child.
-
E.
stepChild
Indicates a parent–child relationship where the child is related to a parent’s spouse but is not the biological or adopted child of that spouse.
- 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_69a498d883a48190bfdca525296ef7ee |
completed | March 1, 2026, 7:51 p.m. |
| NER | Named-entity recognition | batch_69a4c3187f248190a5813274b0ef944d |
completed | March 1, 2026, 10:52 p.m. |
| PD | Predicate disambiguation | batch_69a4befcabdc8190a9f05d002603f81c |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:59 p.m.