Triple
T35332702
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madame de Merret |
E1020367
|
entity |
| Predicate | relationshipTypeWithSpanishOfficer |
P10690
|
FINISHED |
| Object | adulterous love affair |
—
|
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: adulterous love affair | Statement: [Madame de Merret, relationshipTypeWithSpanishOfficer, adulterous love affair]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWithSpanishOfficer Context triple: [Madame de Merret, relationshipTypeWithSpanishOfficer, adulterous love affair]
-
A.
relationshipToAuthorities
Indicates the nature or type of connection, role, or standing that an entity has in relation to governing or official authorities.
-
B.
relationshipTypeWithBlancaTrueba
Indicates that the subject has a specific type of relationship with Blanca Trueba.
-
C.
isOfficerOf
Indicates that one entity holds an official position, role, or office within another entity (such as an organization, group, or institution).
-
D.
governingRelation
Indicates a relationship in which one entity exercises authority, control, or regulatory power over another.
-
E.
relationshipType
chosen
Indicates the specific kind of relationship that exists between two or more entities.
- 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_69f76deacf4481908e7735a5a7715b0a |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a037c8c34f88190ace26f555827f23e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0324d08190ac5b610cc0f6a38c |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:03 p.m.