Triple
T2198700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Her |
E50437
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Chris Pratt |
E81319
|
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: Chris Pratt | Statement: [Her, castMember, Chris Pratt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Chris Pratt Context triple: [Her, castMember, Chris Pratt]
-
A.
Chris Pratt
chosen
Chris Pratt is an American actor known for his leading roles in blockbuster films such as Guardians of the Galaxy and Jurassic World, as well as his earlier television work on Parks and Recreation.
-
B.
Ryan Reynolds
Ryan Reynolds is a Canadian-American actor and producer known for his charismatic performances and sharp comedic timing in films such as Deadpool, The Proposal, and Free Guy.
-
C.
Will Arnett
Will Arnett is a Canadian-American actor and comedian best known for his deep-voiced comedic roles in television series like "Arrested Development" and in animated films.
-
D.
Patrick Wilson
Patrick Wilson is an American actor known for his roles in major horror franchises like The Conjuring and Insidious, as well as superhero and blockbuster films.
-
E.
Brad Fuller
Brad Fuller is a film editor known for his work on the documentary "He Named Me Malala."
- 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_69a88b044ab48190add007487680f009 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abbf7b65cc8190bcc5a5c52b90f33b |
completed | March 7, 2026, 6:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae5db9b0208190a63a75c86ea9dcff |
completed | March 9, 2026, 5:42 a.m. |
Created at: March 4, 2026, 7:46 p.m.