Triple
T9626183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Richard Nixon |
E232470
|
entity |
| Predicate | father |
P120
|
FINISHED |
| Object | Frank Nixon |
E813580
|
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: Frank Nixon | Statement: [Richard Nixon, father, Frank Nixon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frank Nixon Context triple: [Richard Nixon, father, Frank Nixon]
-
A.
Frank Nixon
chosen
Frank Nixon was an American grocer and farmer best known as the father of U.S. President Richard Nixon.
-
B.
Donald Nixon
Donald Nixon was an American businessman best known as the younger brother of U.S. President Richard Nixon, whose financial dealings occasionally drew public scrutiny during his brother’s political career.
-
C.
Arthur Nixon
Arthur Nixon is the son of Hannah Nixon, a member of the Nixon family best known for producing U.S. President Richard Nixon.
-
D.
Edward Nixon
Edward Nixon was the youngest brother of U.S. President Richard Nixon, known for his work as a geologist and author.
-
E.
Bill Clement
Bill Clement is a former NHL center who became a prominent American television hockey analyst and commentator.
- 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_69ca848793ec8190a93a12383a754dc0 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9afc9144819084b208c3d04174ba |
completed | April 1, 2026, 10:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d190e691c48190800660aba2e03b56 |
completed | April 4, 2026, 10:29 p.m. |
Created at: March 30, 2026, 8:10 p.m.