Triple
T2047760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Hangover Part II |
E45492
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Justin Bartha |
E223072
|
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: Justin Bartha | Statement: [The Hangover Part II, starring, Justin Bartha]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Justin Bartha Context triple: [The Hangover Part II, starring, Justin Bartha]
-
A.
Justin Bartha
chosen
Justin Bartha is an American actor best known for his roles in the National Treasure films and the comedy franchise The Hangover.
-
B.
Sean Cahill
Sean Cahill is a relative of former Australian professional soccer player Tim Cahill.
-
C.
Jordan Walke
Jordan Walke is a software engineer best known as the original creator of Facebook’s React JavaScript library and the ReasonML language.
-
D.
Drew Bagnell
Drew Bagnell is a roboticist and machine learning researcher known for his work in autonomous systems and his role as a co-founder and chief scientist at Aurora Innovation.
-
E.
Michael Barrett
Michael Barrett is an American cinematographer known for his work on numerous feature films and television projects, including mainstream comedies and action movies.
- 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_69a8891948208190ab7898da21824c77 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb974e8488190887b840c2cb88b3a |
completed | March 7, 2026, 5:36 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae2003e9488190b54ff042c91d4a62 |
completed | March 9, 2026, 1:19 a.m. |
Created at: March 4, 2026, 7:39 p.m.