Triple
T3778403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baronetage of the United Kingdom |
E83361
|
entity |
| Predicate | femaleSpouseStyle |
P32629
|
FINISHED |
| Object | Lady |
—
|
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: Lady | Statement: [Baronetage of the United Kingdom, femaleSpouseStyle, Lady]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: femaleSpouseStyle Context triple: [Baronetage of the United Kingdom, femaleSpouseStyle, Lady]
-
A.
hasSpouseStyle
Indicates a relationship where one entity’s manner, appearance, or behavior resembles or is characteristic of another entity’s spouse.
-
B.
spouseGender
chosen
Indicates the gender of a person’s spouse in a marital relationship.
-
C.
spouseAssociatedWith
Indicates a marital or spousal relationship or close association between two entities.
-
D.
spouseFamilyName
Indicates that the object is the family name (surname) shared by or associated with a person's spouse.
-
E.
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).
- 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_69ad8b235e608190b5a2b1d1bfcef50b |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcc78173081908b230017834cdf9e |
completed | March 8, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69adc050cc5c81909d9855f866f3c26d |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:36 p.m.