Triple
T26249517
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Randalls |
E656541
|
entity |
| Predicate | formerNameOfMistress |
P65
|
FINISHED |
| Object | Miss Taylor |
—
|
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: Miss Taylor | Statement: [Randalls, formerNameOfMistress, Miss Taylor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerNameOfMistress Context triple: [Randalls, formerNameOfMistress, Miss Taylor]
-
A.
hadMistress
Indicates that a person maintained an extramarital or unofficial romantic/sexual relationship with another person.
-
B.
formerName
chosen
Indicates that an entity was previously known by a different name in the past.
-
C.
formerMaster
Indicates that one entity previously held the role of master over another entity, but no longer does so.
-
D.
maidenNameOf
Indicates that one person’s original family surname before marriage is the maiden name of another person.
-
E.
relationshipToMistressPage
Indicates a person’s specific relational role or connection to Mistress Page.
- 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_69ee5b4d25ac819086acb51184602576 |
completed | April 26, 2026, 6:37 p.m. |
| NER | Named-entity recognition | batch_69f7764ab1fc81909f9348db87bd7692 |
completed | May 3, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69f76905d9c88190b1ee810bc9ab644f |
completed | May 3, 2026, 3:25 p.m. |
Created at: April 26, 2026, 9:06 p.m.