Triple
T18926156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maggie Gilkeson |
E462975
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Samuel Jones |
—
|
NE NERFINISHED |
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: Samuel Jones | Statement: [Maggie Gilkeson, relative, Samuel Jones]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Samuel Jones Context triple: [Maggie Gilkeson, relative, Samuel Jones]
-
A.
Samuel Jones
chosen
Samuel Jones is an individual whose full given name is Samuel but is commonly referred to as Sam Jones.
-
B.
Sean Jones
Sean Jones is the main witness and central protagonist in the action-thriller film "Snakes on a Plane," whose testimony puts him in deadly danger during a high-altitude flight.
-
C.
Charles Jones
Charles Jones is a member of the Jones family of professional basketball-playing brothers that includes former NBA center Caldwell Jones.
-
D.
Andrew Hudson
Andrew Hudson is a former South African cricketer who played as a top-order batsman for the national team in the 1990s.
-
E.
Damon Jones
Damon Jones is a content creator best known for his work on the sports-focused show "Benched."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dcfdbbb881909964fa5a75bd0b48 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c9b94e008190a0e9a70aaf6d18ed |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 10, 2026, 11:59 a.m.