Triple
T14879478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dominique Dunne |
E349959
|
entity |
| Predicate | appearedIn |
P795
|
FINISHED |
| Object | Fame |
E575972
|
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: Fame | Statement: [Dominique Dunne, appearedIn, Fame]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fame Context triple: [Dominique Dunne, appearedIn, Fame]
-
A.
Fame
"Fame" is a song by Janet Jackson, known as one of her dance-pop tracks that showcases her signature rhythmic style and performance energy.
-
B.
Fame
chosen
Fame is a 1980 American musical drama film about students at a New York performing arts high school, known for its energetic dance sequences and iconic title song.
-
C.
Fame
Fame was a record label associated with releasing music by the British rock band Marillion and other artists.
-
D.
Fame
Fame was a ship that took part in the 1760 Battle of the Restigouche during the final stages of the French and Indian War.
-
E.
Fame
"Fame" is a hip-hop track by GZA that reflects on the nature of celebrity and recognition through his characteristic intricate wordplay and storytelling.
- 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_69d822ee4f408190b6ac3b2fa434f0df |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69ded5e622388190b2bf91cd10b9821d |
completed | April 15, 2026, 12:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe6b5670108190b41ef95dc318be60 |
completed | May 8, 2026, 11:01 p.m. |
Created at: April 10, 2026, 1:55 a.m.