Triple
T3023457
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Airport (film score) |
E82518
|
entity |
| Predicate | partOfWorkPeriodOf |
P4343
|
FINISHED |
| Object | late career of Alfred Newman |
—
|
LITERAL 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: late career of Alfred Newman | Statement: [Airport (film score), partOfWorkPeriodOf, late career of Alfred Newman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfWorkPeriodOf Context triple: [Airport (film score), partOfWorkPeriodOf, late career of Alfred Newman]
-
A.
workPeriod
Indicates the span of time during which an entity is engaged in a particular work or employment activity.
-
B.
refersToPeriod
chosen
Indicates that one entity designates, references, or is associated with a specific time period or interval.
-
C.
partOfWorkType
Indicates that something is a component, subtype, or specific category within a broader type of work.
-
D.
periodizedAs
Indicates that something has been divided or organized into distinct time periods according to a particular periodization scheme.
-
E.
continuedIntoPeriod
Indicates that an action, state, or relationship that began earlier persisted without interruption into a specified later time period.
- 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_69ad8b1fb34081908c1b873e2b7273e1 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9ab8e0a48190ac79e674abd181cf |
completed | March 8, 2026, 3:50 p.m. |
| PD | Predicate disambiguation | batch_69ad961c430c8190ac48f2e3c7e7c649 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3 p.m.