Triple
T23145904
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Streak |
E577584
|
entity |
| Predicate | significantWorkFor |
P65731
|
FINISHED |
| Object | Ray Stevens |
—
|
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: Ray Stevens | Statement: [The Streak, significantWorkFor, Ray Stevens]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: significantWorkFor Context triple: [The Streak, significantWorkFor, Ray Stevens]
-
A.
significantWorkHeld
Indicates that an entity possesses, houses, or maintains an important or notable work (such as an artwork, document, or creation) in its collection or custody.
-
B.
notableWorkPerformed
Indicates that an entity has created, executed, or contributed significantly to a particular work that is recognized as notable or important.
-
C.
significantOccupation
Indicates that an occupation plays a major or defining role in an entity’s life, status, or identity.
-
D.
showsWorkOf
Indicates that one entity presents, exhibits, or displays the work or creations produced by another entity.
-
E.
keyWorkOf
chosen
Indicates that the subject is a central, defining, or most important work created by the object (such as an artist, author, or creator).
- 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_69e245f8e6248190ba3d58e068b4dccb |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18ece211c81908b53e98f0acae09a |
completed | April 29, 2026, 4:53 a.m. |
| PD | Predicate disambiguation | batch_69ef89f83b108190aaaa1db6221fc163 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:01 p.m.