Triple
T14878038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Team Downey |
E349919
|
entity |
| Predicate | hasKeyPerson |
P256
|
FINISHED |
| Object | Robert Downey Jr. |
E13443
|
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: Robert Downey Jr. | Statement: [Team Downey, hasKeyPerson, Robert Downey Jr.]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Robert Downey Jr. Context triple: [Team Downey, hasKeyPerson, Robert Downey Jr.]
-
A.
Robert Downey Jr.
chosen
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.
-
B.
Avri Roel Downey
Avri Roel Downey is the daughter of actor Robert Downey Jr. and producer Susan Downey.
-
C.
Tom Hollander
Tom Hollander is an English actor known for his versatile performances in film, television, and theatre, including roles in "In the Loop," "Pride & Prejudice," and the series "Rev."
-
D.
Chris Evans
Chris Evans is an American actor best known for portraying Captain America in the Marvel Cinematic Universe.
-
E.
Chris Evans
Chris Evans is a British television and radio presenter and producer known for hosting shows such as "The Big Breakfast," "TFI Friday," and BBC Radio 2's breakfast program.
- 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_69d822ee4f408190b6ac3b2fa434f0df |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69ded5e4e4448190a8796573bc6d1069 |
completed | April 15, 2026, 12:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe72ac9f6481908f7b4f63a11fe16c |
completed | May 8, 2026, 11:33 p.m. |
Created at: April 10, 2026, 1:55 a.m.