Triple
T30892723
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | De Lacey family |
E786944
|
entity |
| Predicate | includesDaughter |
P24357
|
FINISHED |
| Object | Agatha De Lacey |
—
|
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: Agatha De Lacey | Statement: [De Lacey family, includesDaughter, Agatha De Lacey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesDaughter Context triple: [De Lacey family, includesDaughter, Agatha De Lacey]
-
A.
hasDaughterWith
Indicates that two entities share a parental relationship in which they have at least one daughter together.
-
B.
onlyDaughterOf
Indicates that the subject is the one and only female child (daughter) of the specified parent or parents.
-
C.
consideredDaughterOf
Indicates that one entity is regarded or treated as the daughter of another entity, whether by biology, law, or social recognition.
-
D.
daughterOf
chosen
Indicates that one person is the female child (daughter) of another person.
-
E.
raisesAsDaughter
Indicates that one entity brings up and cares for another as their daughter, in a parental role.
- 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_69f224bbfa7c81908448e0c261c523e3 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a00ac5654a0819090701f61a5802d64 |
completed | May 10, 2026, 4:03 p.m. |
| PD | Predicate disambiguation | batch_6a00ab94b5e881909e15d1342e5f43be |
completed | May 10, 2026, 4 p.m. |
Created at: April 29, 2026, 8:49 p.m.