Triple
T9936890
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jon Voight |
E193981
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object | James Haven |
E224853
|
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: James Haven | Statement: [Jon Voight, hasChild, James Haven]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: James Haven Context triple: [Jon Voight, hasChild, James Haven]
-
A.
James Haven
chosen
James Haven is an American actor and producer best known as the older brother of actress and filmmaker Angelina Jolie.
-
B.
William Humphries
William Humphries is best known as the father of former NBA player Kris Humphries.
-
C.
Henry McHenry
Henry McHenry is an American paleoanthropologist and professor known for his research on human evolution, particularly the biomechanics and locomotion of early hominins.
-
D.
Gridley Bryant
Gridley Bryant was a 19th-century American civil engineer best known for pioneering early railroad engineering and construction techniques in the United States.
-
E.
Charles Faulkner
Charles Faulkner was a 19th-century British designer and partner in the influential Arts and Crafts firm Morris, Marshall, Faulkner & Co.
- 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_69ca82e409348190a393777356b80a2a |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb5e4e19881909879b394090d6629 |
completed | April 2, 2026, 12:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d228e7247c81908dbba76199f2e93f |
completed | April 5, 2026, 9:18 a.m. |
Created at: March 30, 2026, 8:44 p.m.