Triple
T2884793
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First Lady |
E59480
|
entity |
| Predicate | genderVariantOf |
P21356
|
FINISHED |
| Object | First Gentleman |
—
|
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: First Gentleman | Statement: [First Lady, genderVariantOf, First Gentleman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: genderVariantOf Context triple: [First Lady, genderVariantOf, First Gentleman]
-
A.
genderReversalOf
chosen
Indicates that one entity is a counterpart of another with the same role or characteristics but with the opposite gender.
-
B.
genderRule
Indicates a rule or constraint that determines how gender-related properties or classifications should be assigned or interpreted in a given context.
-
C.
genderDivision
Indicates a relationship where roles, responsibilities, or categories are separated or distinguished based on gender.
-
D.
genderCategories
Indicates the classification of an entity into one or more gender-related categories or identities.
-
E.
genderUsage
Indicates how a particular gender is applied, referenced, or treated within a given context or system.
- 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_69ab4ac739188190a112f42a5a69c951 |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abe04476588190b0db0880e14c79b5 |
completed | March 7, 2026, 8:22 a.m. |
| PD | Predicate disambiguation | batch_69abdd15cbf08190bf7fea5ea516848a |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 10:03 p.m.