Triple
T8147241
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Janet Sarbanes |
E190243
|
entity |
| Predicate | father |
P120
|
FINISHED |
| Object | Paul Sarbanes |
E34996
|
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: Paul Sarbanes | Statement: [Janet Sarbanes, father, Paul Sarbanes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Sarbanes Context triple: [Janet Sarbanes, father, Paul Sarbanes]
-
A.
Paul Sarbanes
chosen
Paul Sarbanes was a long-serving U.S. Senator from Maryland best known for co-authoring major corporate governance reforms in the early 2000s.
-
B.
John Sarbanes
John Sarbanes is an American politician and attorney who has served as a Democratic U.S. Representative from Maryland.
-
C.
Janet Sarbanes
Janet Sarbanes is an American writer and academic known for her work in fiction and critical essays, and as the daughter of the late U.S. Senator Paul Sarbanes.
-
D.
Dennis Hastert
Dennis Hastert is an American Republican politician who served as the 51st Speaker of the U.S. House of Representatives from 1999 to 2007.
-
E.
Henry Waxman
Henry Waxman is a longtime Democratic U.S. Congressman from California known for his influential role in health care, environmental, and consumer protection legislation.
- 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_69ca82be7ba8819087de0147e9292c83 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb447d6b1881908ff3fa25af6b4e80 |
completed | March 31, 2026, 3:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc94b667d88190a0b47c7e0e07f338 |
completed | April 1, 2026, 3:44 a.m. |
Created at: March 30, 2026, 5:36 p.m.