Triple
T36431898
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wendell H. Ford |
E897465
|
entity |
| Predicate | succeededByAsGovernorOfKentucky |
P83713
|
FINISHED |
| Object |
Julian Carroll
Julian Carroll is an American Democratic politician who served as the 54th governor of Kentucky in the 1970s.
|
E2184051
|
NE FINISHED |
How this triple was built (3 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: Julian Carroll | Statement: [Wendell H. Ford, succeededByAsGovernorOfKentucky, Julian Carroll]
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: Julian Carroll Triple: [Wendell H. Ford, succeededByAsGovernorOfKentucky, Julian Carroll]
Generated description
Julian Carroll is an American Democratic politician who served as the 54th governor of Kentucky in the 1970s.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: succeededByAsGovernorOfKentucky Context triple: [Wendell H. Ford, succeededByAsGovernorOfKentucky, Julian Carroll]
-
A.
succeededByAsGovernorOfIndiana
Indicates that one person directly followed another in holding the office of Governor of Indiana.
-
B.
succeededBy (Governor of Tennessee)
Indicates that one individual directly follows another in holding the office of Governor of Tennessee.
-
C.
succeededBy (Governor of Virginia)
Indicates that one individual directly followed another in holding the office of Governor of Virginia.
-
D.
succeededInOfficeAsGovernorBy
chosen
Indicates that one individual’s term as governor ended and was directly followed by another individual’s term in the same office.
-
E.
succeededBy (Governor of Pennsylvania)
Indicates that one individual directly follows another in holding the office of Governor of Pennsylvania.
- F. None of above.
Provenance (6 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_69f76e56636481908eda808ab0273401 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a00708ab11081909641d245c4282aa0 |
completed | May 10, 2026, 11:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a39c4141d608190a18abb500b6e8f9a |
completed | June 22, 2026, 11:24 p.m. |
| NEDg | Description generation | batch_6a39c6b749d48190905c24513b8f8236 |
completed | June 22, 2026, 11:35 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a39c7400cd88190b5dedbe938d6bda8 |
completed | June 22, 2026, 11:37 p.m. |
| PD | Predicate disambiguation | batch_6a00703daa0081908903ce3a28084d35 |
completed | May 10, 2026, 11:47 a.m. |
Created at: May 3, 2026, 4:10 p.m.