Triple
T29241971
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | I've Got a Lovely Bunch of Coconuts |
E741337
|
entity |
| Predicate | alsoCreditedTo |
P66001
|
FINISHED |
| Object | Harold Elton |
—
|
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: Harold Elton | Statement: [I've Got a Lovely Bunch of Coconuts, alsoCreditedTo, Harold Elton]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alsoCreditedTo Context triple: [I've Got a Lovely Bunch of Coconuts, alsoCreditedTo, Harold Elton]
-
A.
oftenCreditedTo
Indicates that something (such as a work, idea, or achievement) is frequently attributed or assigned as originating from a particular entity, whether or not that attribution is fully accurate.
-
B.
associatedActOfCreator
Indicates a relationship where an act is linked to the creator responsible for or connected with that act.
-
C.
directorAlsoStarred
Indicates that the person who directed a work also acted or performed as a star in that same work.
-
D.
creditedIn
chosen
Indicates that an entity is acknowledged or listed as a contributor or source within a particular work, record, or context.
-
E.
alsoProducedAs
Indicates that the same work, content, or product has been created or released in an additional form, version, or medium.
- 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_69f0911dd6fc819097d1abb287016489 |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f66486470c8190b3895a34deae626a |
completed | May 2, 2026, 8:54 p.m. |
| PD | Predicate disambiguation | batch_69f660f2e3708190ab658652bcfc04d0 |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 28, 2026, 12:31 p.m.