Triple
T9077960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liza Minnelli |
E217535
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Mark Gero |
E217535
|
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: Mark Gero | Statement: [Liza Minnelli, spouse, Mark Gero]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Gero Context triple: [Liza Minnelli, spouse, Mark Gero]
-
A.
Mark Gero
chosen
Mark Gero is an American sculptor and stage designer best known for his marriage to entertainer Liza Minnelli.
-
B.
Byron McLaughlin
Byron McLaughlin is a former American Major League Baseball pitcher who played primarily for the Seattle Mariners in the late 1970s and early 1980s.
-
C.
Allan Moyle
Allan Moyle is a Canadian film director and screenwriter best known for his cult-favorite youth and counterculture dramas, including the 1990 film "Pump Up the Volume."
-
D.
Steve Judd
Steve Judd is the aging, principled former lawman at the heart of the Western film "Ride the High Country," whose moral integrity drives the story’s central conflict.
-
E.
Joe Tonahill
Joe Tonahill was an American defense attorney best known for serving on the legal team that defended Jack Ruby after Ruby killed Lee Harvey Oswald.
- 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_69ca83d6c14c8190bc056d927f00a2a2 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc95c7d3688190a4c1c6a92965eae4 |
completed | April 1, 2026, 3:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d065bddf1c81909b6134179fe92556 |
completed | April 4, 2026, 1:13 a.m. |
Created at: March 30, 2026, 7:12 p.m.