Triple
T13193882
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Courtney Kennedy Hill |
E314060
|
entity |
| Predicate | uncle |
P8496
|
FINISHED |
| Object | John F. Kennedy |
E305
|
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: John F. Kennedy | Statement: [Courtney Kennedy Hill, uncle, John F. Kennedy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John F. Kennedy Context triple: [Courtney Kennedy Hill, uncle, John F. Kennedy]
-
A.
John F. Kennedy
chosen
John F. Kennedy was the 35th president of the United States, known for his leadership during the Cold War, the Cuban Missile Crisis, and the early stages of the civil rights movement before his assassination in 1963.
-
B.
Presidente Kennedy
Presidente Kennedy is a small coastal municipality in the Brazilian state of Espírito Santo, known for its beaches and growing oil and gas-related economic activities.
-
C.
JFK
JFK is John F. Kennedy International Airport, a major international air travel hub serving New York City.
-
D.
RJFK
RJFK is the ICAO airport code for Kagoshima Airport, a regional and domestic aviation hub on Japan’s Kyushu island.
-
E.
John Fitzgerald
John Fitzgerald is the founder of the global financial services firm Cantor Fitzgerald.
- 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_69d806ae1e08819090d95bfe1538cc17 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98c6158e4819082c8ad75b4dfdd90 |
completed | April 10, 2026, 11:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6f600f7a08190bcdd80d5563517c3 |
completed | May 3, 2026, 7:15 a.m. |
Created at: April 9, 2026, 9:16 p.m.