Triple
T7818256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joe Spinell |
E181064
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Rocky |
E10224
|
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: Rocky | Statement: [Joe Spinell, notableWork, Rocky]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rocky Context triple: [Joe Spinell, notableWork, Rocky]
-
A.
Rocky
chosen
Rocky is a classic 1976 American sports drama film starring Sylvester Stallone as an underdog boxer who gets an unlikely shot at the world heavyweight title.
-
B.
Rocky
Rocky is a stage musical adaptation of the iconic boxing film franchise, known for its dramatic underdog story and innovative, cinematic-style fight sequences on Broadway.
-
C.
Rocky
Rocky is the nickname of Rocky Wirtz, the late principal owner and chairman of the NHL’s Chicago Blackhawks.
-
D.
Rocky
Rocky is a resourceful mixed-breed pup from PAW Patrol known for his love of recycling and inventive use of repurposed materials to solve problems.
-
E.
Rocky
Rocky is the nickname of Rocky Anderson, an American lawyer and politician who served as mayor of Salt Lake City.
- 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_69ca828153f48190bdb27ac46f8e0745 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69caf9708bdc8190a5154efe0f96f458 |
completed | March 30, 2026, 10:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb149266e88190a582b11d68702a6a |
completed | March 31, 2026, 12:25 a.m. |
Created at: March 30, 2026, 4:40 p.m.