Triple
T31790429
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | House of Estrées |
E811447
|
entity |
| Predicate | Gabrielle d’Estrées-role |
P154906
|
FINISHED |
| Object | mistress of Henry IV of France |
—
|
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: mistress of Henry IV of France | Statement: [House of Estrées, Gabrielle d’Estrées-role, mistress of Henry IV of France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Gabrielle d’Estrées-role Context triple: [House of Estrées, Gabrielle d’Estrées-role, mistress of Henry IV of France]
-
A.
RichelieuTitle
Indicates that an entity holds or is associated with a noble or official title specifically linked to Richelieu.
-
B.
servedAsLadyInWaitingTo
Indicates that one person held the role of lady-in-waiting in service to another, typically a female member of royalty or nobility.
-
C.
Aramis
Indicates that an entity is named or identified as "Aramis."
-
D.
notableCourtier
chosen
Indicates that a person served as a courtier and is recognized as particularly prominent or noteworthy in that role.
-
E.
Athos
Indicates a relationship or action involving Athos, such as participation, association, or attribution connected to that entity.
- 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_69f348e60748819082dcaa7792659803 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6ac186f888190979084647ec49b6a |
completed | May 3, 2026, 1:59 a.m. |
| PD | Predicate disambiguation | batch_69f6aa21f2508190a204a424ffc00ca6 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 30, 2026, 11:39 p.m.