Triple
T28463920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nando Torres |
E720235
|
entity |
| Predicate | hasOnScreenMother |
P112429
|
FINISHED |
| Object | Allison Torres |
—
|
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: Allison Torres | Statement: [Nando Torres, hasOnScreenMother, Allison Torres]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOnScreenMother Context triple: [Nando Torres, hasOnScreenMother, Allison Torres]
-
A.
hasOnScreenFamilyMember
chosen
Indicates that one entity appears on screen as a family member of another entity.
-
B.
hasFictionalMother
Indicates that one entity is the fictional mother of another entity within a narrative or fictional context.
-
C.
heldByMotherOf
Indicates that something is possessed, owned, or physically held by the mother of a given entity.
-
D.
hasScreen
Indicates that an entity is equipped with or includes a screen or display component.
-
E.
isMotherOf
Indicates that one entity is the female parent who has given birth to or legally/ socially parents the other 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_69f01a58a67c819097936d9e8da8d6e6 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f6c49627908190b3553474c7c3072b |
completed | May 3, 2026, 3:44 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f23ae081909a52801266063a3c |
completed | May 3, 2026, 3:41 a.m. |
Created at: April 28, 2026, 2:43 a.m.