Triple
T28405161
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Impératrice des Français |
E719506
|
entity |
| Predicate | thirdHolderSpouse |
P178032
|
FINISHED |
| Object | Napoleon III of France |
—
|
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: Napoleon III of France | Statement: [Impératrice des Français, thirdHolderSpouse, Napoleon III of France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: thirdHolderSpouse Context triple: [Impératrice des Français, thirdHolderSpouse, Napoleon III of France]
-
A.
firstHolderSpouseOf
Indicates that the first holder in the relation is the spouse (married partner) of the other holder.
-
B.
thirdHusband
Indicates that one person is the third man to be married to another person.
-
C.
spouseOfHead
Indicates that one person is the married partner of the individual who holds the position of head (e.g., head of a household, organization, or state).
-
D.
titleHolderSpouseInstanceOf
Indicates that the spouse of a title holder is an instance of a specified role, status, or class related to that title.
-
E.
thirdHolder
Indicates that an entity serves as the third holder or possessor of another entity in a sequence or ordered set of holders.
- F. None of above. chosen
Provenance (4 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_69eff6efd1b08190ae3cefd4f11388a2 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f707f7959881908f037f0d6b1d0c36 |
completed | May 3, 2026, 8:31 a.m. |
| PD | Predicate disambiguation | batch_69f700fc274c8190a128593dc7c7abd0 |
completed | May 3, 2026, 8:02 a.m. |
| PDg | Predicate description generation | batch_69f707f380388190954b79d52a321921 |
completed | May 3, 2026, 8:31 a.m. |
Created at: April 28, 2026, 1:22 a.m.