Triple
T9263929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nancy Kassebaum |
E222646
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Kassebaum
Kassebaum is the surname most prominently associated with Nancy Kassebaum, a former United States senator from Kansas known for her moderate Republican views and bipartisan work.
|
E791019
|
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: Kassebaum | Statement: [Nancy Kassebaum, familyName, Kassebaum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kassebaum Context triple: [Nancy Kassebaum, familyName, Kassebaum]
-
A.
T. T. Waterman
T. T. Waterman was an American anthropologist and ethnographer known for his work documenting Native Californian cultures in the early 20th century.
-
B.
Arlen
Arlen is a given name most notably borne by Arlen Specter, a long-serving United States Senator from Pennsylvania.
-
C.
Howard E. Smith
Howard E. Smith is a film editor best known for his work on major Hollywood productions, including the shark thriller "Deep Blue Sea."
-
D.
Howard E. Smith
Howard E. Smith is a film editor best known for his work on the acclaimed drama "Glengarry Glen Ross."
-
E.
Howard E. Smith
Howard E. Smith is a film editor best known for his work on the thriller "Snakes on a Plane."
- 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: Kassebaum Triple: [Nancy Kassebaum, familyName, Kassebaum]
Generated description
Kassebaum is the surname most prominently associated with Nancy Kassebaum, a former United States senator from Kansas known for her moderate Republican views and bipartisan work.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kassebaum Target entity description: Kassebaum is the surname most prominently associated with Nancy Kassebaum, a former United States senator from Kansas known for her moderate Republican views and bipartisan work.
-
A.
T. T. Waterman
T. T. Waterman was an American anthropologist and ethnographer known for his work documenting Native Californian cultures in the early 20th century.
-
B.
Arlen
Arlen is a given name most notably borne by Arlen Specter, a long-serving United States Senator from Pennsylvania.
-
C.
Howard E. Smith
Howard E. Smith is a film editor best known for his work on major Hollywood productions, including the shark thriller "Deep Blue Sea."
-
D.
Howard E. Smith
Howard E. Smith is a film editor best known for his work on the acclaimed drama "Glengarry Glen Ross."
-
E.
Howard E. Smith
Howard E. Smith is a film editor best known for his work on the thriller "Snakes on a Plane."
- 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_69ca841f2e808190a64f4c31903a1332 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd0719eee081909e21ecb9d6dd0b49 |
completed | April 1, 2026, 11:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0c736ccd8819081d2c5a6be11ac36 |
completed | April 4, 2026, 8:09 a.m. |
| NEDg | Description generation | batch_69d0c850d65c8190b2bf5da194466dd7 |
completed | April 4, 2026, 8:14 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d0ca3b77e081908fdcc1aafaf2344a |
completed | April 4, 2026, 8:22 a.m. |
Created at: March 30, 2026, 7:32 p.m.