Triple
T28963936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Goodbye Norma Jean |
E731985
|
entity |
| Predicate | openingLyricOf |
P15282
|
FINISHED |
| Object | Candle in the Wind |
—
|
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: Candle in the Wind | Statement: [Goodbye Norma Jean, openingLyricOf, Candle in the Wind]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openingLyricOf Context triple: [Goodbye Norma Jean, openingLyricOf, Candle in the Wind]
-
A.
hasOpeningLyric
chosen
Indicates that one entity serves as the opening lyric of another entity, typically a song or musical work.
-
B.
openingVerseBy
Indicates that a work’s opening verse is authored, performed, or otherwise created by the specified entity.
-
C.
openingVerses
Indicates that one text or section contains the initial or introductory verses of another text or composition.
-
D.
openingLine
Indicates that one entity is the first line or initial statement that begins another entity, such as a text, speech, or conversation.
-
E.
openingHymnFor
Indicates that one item serves as the opening hymn for a particular event, service, or ceremony.
- 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_69f043ee242c8190b063248b417c5a69 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f6b49436b0819094e21603054d05d4 |
completed | May 3, 2026, 2:36 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a5fd8481909433e923c5e24e55 |
completed | May 3, 2026, 2:32 a.m. |
Created at: April 28, 2026, 8:51 a.m.