Triple
T19165038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Curt Henderson |
E469156
|
entity |
| Predicate | hasFriend |
P8712
|
FINISHED |
| Object | John Milner |
—
|
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: John Milner | Statement: [Curt Henderson, hasFriend, John Milner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Milner Context triple: [Curt Henderson, hasFriend, John Milner]
-
A.
John Milner
chosen
John Milner is a fictional hot-rod enthusiast and central character from the American Graffiti film series, emblematic of 1960s car culture and teenage rebellion.
-
B.
Jonathan Milner
Jonathan Milner is a British entrepreneur and scientist best known as the co-founder of the life sciences reagents company Abcam.
-
C.
Ian Gilmour
Ian Gilmour was a British Conservative politician and cabinet minister who served in senior roles including Defence Secretary and Lord Privy Seal during the 1970s and early 1980s.
-
D.
Tim Atack
Tim Atack is a British composer and musician known for his film and television scores, including work on projects like "Cemetery Junction."
-
E.
Julian Morris
Julian Morris is a British actor known for his roles in television series such as "Pretty Little Liars," "New Girl," and various film and TV dramas.
- 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_69d8dd09d5a081909ae43c286651ae5a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f15e2720819084b1707497db26a2 |
completed | April 20, 2026, 9:26 a.m. |
Created at: April 10, 2026, 12:06 p.m.