Triple
T38522378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Hagen |
E922519
|
entity |
| Predicate | uncleFigure |
P125154
|
FINISHED |
| Object | Michael Corleone |
—
|
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: Michael Corleone | Statement: [Frank Hagen, uncleFigure, Michael Corleone]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: uncleFigure Context triple: [Frank Hagen, uncleFigure, Michael Corleone]
-
A.
uncle
Indicates a familial relationship where one person is the brother (or brother-in-law) of another person's parent.
-
B.
fictionalUncle
chosen
Indicates that one entity is the uncle of another within a fictional or narrative context.
-
C.
UncleSignificance
Indicates the degree of importance, influence, or meaningful role that an uncle has in relation to another person.
-
D.
uncleOrAuntOf
Indicates that one person is the uncle or aunt of another person, typically as the sibling (or sibling-in-law) of the other person’s parent.
-
E.
halfUncleOf
Indicates a familial relationship where one person is the half-brother of a parent of another person, making him that person's half-uncle.
- 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_69f76ea5f5588190bd0b28c82e975640 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcdaa36f90819093f8661969990c7d |
completed | May 7, 2026, 6:32 p.m. |
| PD | Predicate disambiguation | batch_69fcd8fefc588190b063d7ea1ec87b07 |
completed | May 7, 2026, 6:25 p.m. |
Created at: May 3, 2026, 4:32 p.m.