Triple
T27817451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Buoys |
E702713
|
entity |
| Predicate | songwriterOfHit |
P87641
|
FINISHED |
| Object | Rupert Holmes |
—
|
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: Rupert Holmes | Statement: [The Buoys, songwriterOfHit, Rupert Holmes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: songwriterOfHit Context triple: [The Buoys, songwriterOfHit, Rupert Holmes]
-
A.
songWrittenBy
Indicates that a particular song was created or composed by a specific person or group.
-
B.
notableSongwriterOn
Indicates that one entity is recognized as a notable songwriter contributing to or associated with another entity (such as a musical work or recording).
-
C.
songwritingCredit
chosen
Indicates that one entity is credited as a songwriter or co-songwriter for a musical work associated with another entity.
-
D.
songwriterOn
Indicates that one entity serves as the songwriter or composer responsible for creating the musical content associated with another entity.
-
E.
keySongwriter
Indicates that the subject is the primary or main songwriter responsible for creating the song associated with the object.
- 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_69ef840ad1e88190b5bff2d1ddec8700 |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f6386bdaac819099c2623f898dc26e |
completed | May 2, 2026, 5:46 p.m. |
| PD | Predicate disambiguation | batch_69f6318ae6f08190b3f85f9201046a15 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 27, 2026, 5:46 p.m.