Triple
T1881910
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joey Luft |
E39870
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | Liza Minnelli |
E23314
|
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: Liza Minnelli | Statement: [Joey Luft, sibling, Liza Minnelli]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Liza Minnelli Context triple: [Joey Luft, sibling, Liza Minnelli]
-
A.
Liza Minnelli
chosen
Liza Minnelli is an American actress and singer best known for her Academy Award-winning performance in the film "Cabaret" and her powerful stage presence in musical theatre and concerts.
-
B.
Christian Minnelli
Christian Minnelli is a child of acclaimed American film director Vincente Minnelli.
-
C.
Denise "Danielle" Minnelli
Denise "Danielle" Minnelli was the fourth wife of acclaimed American film director Vincente Minnelli.
-
D.
Lester Anthony Minnelli
Lester Anthony Minnelli, better known as Vincente Minnelli, was an influential American film director famed for his visually lavish and innovative Hollywood musicals and dramas, including classics like "An American in Paris" and "Gigi."
-
E.
Bette Midler
Bette Midler is an American singer, actress, and comedian renowned for her powerful vocals, theatrical performances, and acclaimed work in film, television, and on stage.
- 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_69a88633e4fc8190b7eb40463e048ec5 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb0fb95b48190af5286662c8b9734 |
completed | March 7, 2026, 5 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adeae631488190b5b4a8137112e568 |
completed | March 8, 2026, 9:32 p.m. |
Created at: March 4, 2026, 7:34 p.m.