Triple
T16096969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marlo Thomas |
E390511
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Phil Donahue |
E507492
|
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: Phil Donahue | Statement: [Marlo Thomas, spouse, Phil Donahue]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Phil Donahue Context triple: [Marlo Thomas, spouse, Phil Donahue]
-
A.
Phil Donahue
chosen
Phil Donahue is an American television host and media pioneer best known for creating and hosting the long-running, audience-participation talk show "The Phil Donahue Show."
-
B.
Don Francis
Don Francis is an American epidemiologist and public health official known for his early work on HIV/AIDS research and prevention.
-
C.
Bill Cullen
Bill Cullen was a prolific American radio and television game show host best known for his quick wit and long-running presence on numerous classic quiz and panel programs.
-
D.
Frank Cavett
Frank Cavett was an American screenwriter best known for his work on the classic 1944 film "Going My Way."
-
E.
Tom Snyder
Tom Snyder was an American television personality and pioneering late-night talk show host known for his in-depth, conversational interview style on programs like "Tomorrow" and "The Late Late Show."
- 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_69d87f198bc48190a8b7e53ca15b7ead |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e18593d0fc8190aa3ba3edb4219aaa |
completed | April 17, 2026, 12:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffeb991ba88190ad568a49069f9701 |
completed | May 10, 2026, 2:21 a.m. |
Created at: April 10, 2026, 4:59 a.m.