Triple
T3790453
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MacArthur Park |
E89631
|
entity |
| Predicate | hasRepresentationInTelevision |
P3279
|
FINISHED |
| Object | various television shows set in Los Angeles |
—
|
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: various television shows set in Los Angeles | Statement: [MacArthur Park, hasRepresentationInTelevision, various television shows set in Los Angeles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRepresentationInTelevision Context triple: [MacArthur Park, hasRepresentationInTelevision, various television shows set in Los Angeles]
-
A.
isTelevised
Indicates that an event, program, or activity is broadcast on television for public viewing.
-
B.
televisionWork
Indicates a relationship where a creative work is produced for, broadcast on, or primarily associated with television.
-
C.
introducedOnTV
Indicates that an entity was first presented, revealed, or made known to the public through a television broadcast.
-
D.
televisionShow
chosen
Indicates that one entity is a television show associated with, or featured in relation to, another entity.
-
E.
televisionAdaptationStar
Indicates that a person is a starring actor in a television adaptation of a work.
- 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_69aed9597d6881909b6ee3b9de859223 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeecefa3608190a7a20ed6df6a64b2 |
completed | March 9, 2026, 3:53 p.m. |
| PD | Predicate disambiguation | batch_69aee743c8d08190a9f9c97b836bd703 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:15 p.m.