Triple
T38650312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mrs. Caxton |
E939720
|
entity |
| Predicate | hasSurnameInTitleFamily |
P52579
|
FINISHED |
| Object | Caxton family |
—
|
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: Caxton family | Statement: [Mrs. Caxton, hasSurnameInTitleFamily, Caxton family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSurnameInTitleFamily Context triple: [Mrs. Caxton, hasSurnameInTitleFamily, Caxton family]
-
A.
hasTitleInFamily
Indicates that one entity holds a specific familial title or role in relation to another entity within a family context.
-
B.
hasFamilyNameOf
chosen
Indicates that one entity bears or uses the same family name (surname) as another entity.
-
C.
usedAsTitleCharacterSurname
Indicates that a surname is used as the name of a title character in a work (e.g., book, film, or series).
-
D.
hasFamilyNameInitial
Indicates that an entity’s family name begins with a specified initial letter or character.
-
E.
hasGivenNameInTitle
Indicates that the given name of an entity appears within the title of another 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_69f76ede49648190a48bfe47032a05a3 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a009f53a4948190aef4ede1713e1748 |
completed | May 10, 2026, 3:08 p.m. |
| PD | Predicate disambiguation | batch_6a009edc53d4819080b22c1074a990f3 |
completed | May 10, 2026, 3:06 p.m. |
Created at: May 3, 2026, 4:33 p.m.