Triple
T7231260
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steve Beshear |
E154906
|
entity |
| Predicate | precededBy |
P97
|
FINISHED |
| Object |
Ernie Fletcher
Ernie Fletcher is an American physician and Republican politician who served as the 60th governor of Kentucky from 2003 to 2007.
|
E650654
|
NE FINISHED |
How this triple was built (4 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: Ernie Fletcher | Statement: [Steve Beshear, precededBy, Ernie Fletcher]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ernie Fletcher Context triple: [Steve Beshear, precededBy, Ernie Fletcher]
-
A.
Tom Burleson
Tom Burleson is a retired American professional basketball center best known for his shot-blocking and rebounding in the NBA during the 1970s.
-
B.
Michele Buck
Michele Buck is a British television producer best known for her work on popular drama series such as "Agatha Christie's Marple" and "Poirot."
-
C.
Phil Wenneck
Phil Wenneck is a charismatic, fast-talking schoolteacher and member of the "Wolfpack" whose misadventures drive much of the comedy in The Hangover film series.
-
D.
Randy Bricker
Randy Bricker is a film editor known for his work on horror and genre films, including Texas Chainsaw 3D.
-
E.
Andrew Licht
Andrew Licht is a film producer best known for his work on the horror-comedy movie "Idle Hands."
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Ernie Fletcher Triple: [Steve Beshear, precededBy, Ernie Fletcher]
Generated description
Ernie Fletcher is an American physician and Republican politician who served as the 60th governor of Kentucky from 2003 to 2007.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ernie Fletcher Target entity description: Ernie Fletcher is an American physician and Republican politician who served as the 60th governor of Kentucky from 2003 to 2007.
-
A.
Tom Burleson
Tom Burleson is a retired American professional basketball center best known for his shot-blocking and rebounding in the NBA during the 1970s.
-
B.
Michele Buck
Michele Buck is a British television producer best known for her work on popular drama series such as "Agatha Christie's Marple" and "Poirot."
-
C.
Phil Wenneck
Phil Wenneck is a charismatic, fast-talking schoolteacher and member of the "Wolfpack" whose misadventures drive much of the comedy in The Hangover film series.
-
D.
Randy Bricker
Randy Bricker is a film editor known for his work on horror and genre films, including Texas Chainsaw 3D.
-
E.
Andrew Licht
Andrew Licht is a film producer best known for his work on the horror-comedy movie "Idle Hands."
- F. None of above. chosen
Provenance (5 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_69c68811dd1c8190ac460bb39e64e1f0 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea0f09648190b285993556f704d5 |
completed | March 27, 2026, 8:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7cc22a39481909a2f38014260f302 |
completed | March 28, 2026, 12:40 p.m. |
| NEDg | Description generation | batch_69c7cd95c8c48190aa4c7d086f03bc0f |
completed | March 28, 2026, 12:46 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7ce1b5e0081908d8e68fb1c0bfd3e |
completed | March 28, 2026, 12:48 p.m. |
Created at: March 27, 2026, 2:54 p.m.