Triple
T19351201
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grand Theft Auto |
E484022
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Elizabeth Rogers |
—
|
NE NERFINISHED |
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: Elizabeth Rogers | Statement: [Grand Theft Auto, starring, Elizabeth Rogers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elizabeth Rogers Context triple: [Grand Theft Auto, starring, Elizabeth Rogers]
-
A.
Elizabeth Rogers
chosen
Elizabeth Rogers was an American actress known for her film and television roles in the 1960s and 1970s.
-
B.
Lisa Rogers
Lisa Rogers is a member of the Rogers family, known as the daughter of Canadian businessman and media magnate Ted Rogers.
-
C.
Rosemary Squire
Rosemary Squire is a prominent British theatre entrepreneur and producer, best known as the co-founder and former joint chief executive of the Ambassador Theatre Group, one of the world’s largest live theatre companies.
-
D.
Emily Lloyd
Emily Lloyd is a British actress best known for her acclaimed breakthrough role in the 1987 film "Wish You Were Here."
-
E.
Anna Rampton
Anna Rampton is a fictional senior BBC executive in the British mockumentary series "W1A," known for her terse manner and corporate jargon.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8d244f8819080eb1f3491300db2 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e61904a878819084d58ed3b7d8a978 |
completed | April 20, 2026, 12:16 p.m. |
Created at: April 10, 2026, 1:34 p.m.