Triple
T17864829
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heather Menzies |
E446666
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Robert Urich |
—
|
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: Robert Urich | Statement: [Heather Menzies, spouse, Robert Urich]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Robert Urich Context triple: [Heather Menzies, spouse, Robert Urich]
-
A.
Robert Urich
chosen
Robert Urich was an American actor best known for his roles in television series such as "Vega$," "Spenser: For Hire," and "Lonesome Dove."
-
B.
Matthew Modine
Matthew Modine is an American actor best known for his roles in films like "Full Metal Jacket" and the series "Stranger Things."
-
C.
Tom Berenger
Tom Berenger is an American actor best known for his roles in films such as "Platoon," "The Big Chill," and "Inception," often portraying tough, complex characters.
-
D.
Miguel Ferrer
Miguel Ferrer was an American character actor known for his intense, often villainous roles in film and television, including notable performances in projects like "RoboCop," "Twin Peaks," and "NCIS: Los Angeles."
-
E.
Jason Patric
Jason Patric is an American film and stage actor known for roles in movies such as "The Lost Boys," "Sleepers," and "Speed 2: Cruise Control."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49792ccf88190a0984963bb385688 |
completed | April 19, 2026, 8:51 a.m. |
Created at: April 10, 2026, 10:17 a.m.