Triple
T28894481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stealing Harvard |
E732801
|
entity |
| Predicate | hasNieceCharacter |
P63741
|
FINISHED |
| Object | Noreen |
—
|
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: Noreen | Statement: [Stealing Harvard, hasNieceCharacter, Noreen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNieceCharacter Context triple: [Stealing Harvard, hasNieceCharacter, Noreen]
-
A.
hasNannyCharacter
Indicates that one entity serves as a nanny or caregiver character for another entity.
-
B.
niece
chosen
Indicates that one person is the female child of another person's sibling or sibling-in-law.
-
C.
nieceOrNephewOf
Indicates that one person is the niece or nephew (the child of a sibling or sibling-in-law) of another person.
-
D.
hasSisterProtagonists
Indicates that the work features two or more main characters who are sisters as its central protagonists.
-
E.
hasPuppetCharacter
Indicates that one entity features, includes, or is associated with a particular puppet character as part of its content or composition.
- 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_69f05b08c2008190ac426a035a2ed66d |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f65aa2c5fc8190a74ea45c30e714d4 |
completed | May 2, 2026, 8:12 p.m. |
| PD | Predicate disambiguation | batch_69f6576487e081908d802f1caf59c423 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 7:58 a.m.