Triple
T14259488
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Downey Jr. |
E353473
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Avri Roel Downey |
E500493
|
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: Avri Roel Downey | Statement: [Robert Downey Jr., child, Avri Roel Downey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Avri Roel Downey Context triple: [Robert Downey Jr., child, Avri Roel Downey]
-
A.
Avri Roel Downey
chosen
Avri Roel Downey is the daughter of actor Robert Downey Jr. and producer Susan Downey.
-
B.
Robert Downey Jr.
Robert Downey Jr. is an acclaimed American actor best known for his charismatic performances in films such as the Iron Man and Avengers series, as well as his critically lauded dramatic roles.
-
C.
Lee Tergesen
Lee Tergesen is an American actor best known for his roles in the HBO series "Oz," the film "Wayne's World," and numerous television dramas and miniseries.
-
D.
Kal Penn
Kal Penn is an American actor and former White House staff member best known for his roles in the "Harold & Kumar" film series and the TV show "House."
-
E.
Indio Falconer Downey
Indio Falconer Downey is an American musician and actor, best known as the son of actor Robert Downey Jr.
- 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_69d8278c43e08190824146f4632b89a5 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de635534988190816fdfb315cd2a3f |
completed | April 14, 2026, 3:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd5bb7e0ac81909d62993689b56f83 |
completed | May 8, 2026, 3:42 a.m. |
Created at: April 10, 2026, 1:09 a.m.