Triple
T694794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rocky film series |
E13871
|
entity |
| Predicate | notableCharacter |
P1481
|
FINISHED |
| Object | Adrian Pennino |
E77293
|
NE FINISHED |
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: Adrian Pennino | Statement: [Rocky film series, notableCharacter, Adrian Pennino]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adrian Pennino Context triple: [Rocky film series, notableCharacter, Adrian Pennino]
-
A.
Adrian Pennino
chosen
Adrian Pennino is a shy pet shop worker who becomes Rocky Balboa’s devoted wife and emotional anchor in the Rocky film series.
-
B.
Michael Convertino
Michael Convertino is an American film composer known for scoring a variety of movies and television projects.
-
C.
Ronald Mariano
Ronald Mariano is an American politician serving as Speaker of the Massachusetts House of Representatives.
-
D.
Jake Nava
Jake Nava is a British music video director known for his visually striking work with major artists across pop and R&B.
-
E.
Jason Hudson
Jason Hudson was the brother of singer and actress Jennifer Hudson, tragically murdered in a widely publicized 2008 family shooting in Chicago.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a493406c408190957eeec9048a8fb6 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a0c3f39c8190a3014df428817492 |
completed | March 1, 2026, 8:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7a3a6bcf88190aff5bd3db264f475 |
completed | March 4, 2026, 3:14 a.m. |
Created at: March 1, 2026, 7:36 p.m.