Triple
T35576736
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Napoléon III |
E1028096
|
entity |
| Predicate | throughMother |
P94441
|
FINISHED |
| Object | Hortense de Beauharnais |
—
|
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: Hortense de Beauharnais | Statement: [Napoléon III, throughMother, Hortense de Beauharnais]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: throughMother Context triple: [Napoléon III, throughMother, Hortense de Beauharnais]
-
A.
motherIn
Indicates that one entity is the mother of another entity within a specified context or domain.
-
B.
motherMother
chosen
Indicates that one entity is the mother of another entity’s mother (i.e., the maternal grandmother relationship).
-
C.
throughParent
Indicates that the relationship or connection between two entities is mediated or established via a parent entity in a hierarchical structure.
-
D.
stepMotherOf
Indicates that one person is the female spouse or partner of a parent of another person, but is not that person's biological or adoptive mother.
-
E.
motherWas
Indicates that one entity was the mother (biological or adoptive) of another entity at some time in the past.
- 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_69f76e0386688190b931bacdc145938c |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f79ec355048190af30123ceb6efa2b |
completed | May 3, 2026, 7:15 p.m. |
| PD | Predicate disambiguation | batch_69f79e4bdbcc8190be7a0d2cf8a77b64 |
completed | May 3, 2026, 7:13 p.m. |
Created at: May 3, 2026, 4:04 p.m.