Triple
T7731074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donna Sheridan |
E175252
|
entity |
| Predicate | sings |
P12693
|
FINISHED |
| Object | Dancing Queen |
E48051
|
NE 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: Dancing Queen | Statement: [Donna Sheridan, sings, Dancing Queen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dancing Queen Context triple: [Donna Sheridan, sings, Dancing Queen]
-
A.
Dancing Queen
chosen
"Dancing Queen" is a 1976 disco-pop hit by the Swedish group ABBA, widely regarded as one of their signature songs and a classic of the genre.
-
B.
Well Done Abba
Well Done Abba is a 2009 Indian satirical comedy film directed by Shyam Benegal that critiques bureaucratic corruption and rural governance through a humorous narrative.
-
C.
Five Stairsteps
Five Stairsteps were an American family soul group best known for their 1970 hit single "O-o-h Child."
-
D.
Let's Dance
"Let's Dance" is a 1950 musical comedy film starring Fred Astaire that showcases his signature song-and-dance performances.
-
E.
Let's Dance
"Let's Dance" is a high-energy rock cover of the 1962 Chris Montez hit, recorded by the Ramones and featured on their debut album.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c6995e912c81909a49a2657103f786 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c70336aafc819099a060950ab8922f |
completed | March 27, 2026, 10:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8b52e176481908595fea4ace7a607 |
completed | March 29, 2026, 5:14 a.m. |
Created at: March 27, 2026, 4:06 p.m.