Triple
T33730975
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rocky film series scores |
E864272
|
entity |
| Predicate | composerOfRockyBalboa |
P194143
|
FINISHED |
| Object | Bill Conti |
—
|
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: Bill Conti | Statement: [Rocky film series scores, composerOfRockyBalboa, Bill Conti]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: composerOfRockyBalboa Context triple: [Rocky film series scores, composerOfRockyBalboa, Bill Conti]
-
A.
composerOfRockyIII
Indicates that one entity is the composer who created the musical score for the film "Rocky III" in relation to another entity.
-
B.
composerOfRockyV
Indicates that the subject is the composer of the music for the film "Rocky V".
-
C.
Larry Schemel
Indicates a relationship or association involving the person named Larry Schemel, such as authorship, participation, or attribution in a given context.
-
D.
Ron Watkins
Indicates a relationship or action involving Ron Watkins, such as authorship, participation, responsibility, or association in a given context.
-
E.
Joseph Alioto
Indicates a relationship or action involving the person named Joseph Alioto, such as authorship, participation, or association in a given context.
- F. None of above. chosen
Provenance (4 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_69f3498a64cc8190b4b414c67b280d93 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fd64bc86848190a49f451a8fc5cf1e |
completed | May 8, 2026, 4:21 a.m. |
| PD | Predicate disambiguation | batch_69fd5ff4a648819090756d90fd195d9a |
completed | May 8, 2026, 4 a.m. |
| PDg | Predicate description generation | batch_69fd64bb345c819096a35c72784a8ce3 |
completed | May 8, 2026, 4:21 a.m. |
Created at: May 1, 2026, 1:44 a.m.