Triple
T3772136
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Goliath |
E83221
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Olivia Thirlby |
E11657
|
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: Olivia Thirlby | Statement: [Goliath, starring, Olivia Thirlby]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Olivia Thirlby Context triple: [Goliath, starring, Olivia Thirlby]
-
A.
Olivia Thirlby
chosen
Olivia Thirlby is an American actress known for her roles in films such as "Juno," "Dredd," and various independent and mainstream productions.
-
B.
Haley Bennett
Haley Bennett is an American actress and singer known for her versatile performances in films such as "The Girl on the Train," "The Magnificent Seven," and "Swallow."
-
C.
Olivia Cooke
Olivia Cooke is an English actress known for her roles in films like "Ready Player One" and the TV series "Bates Motel" and "House of the Dragon."
-
D.
Juno Temple
Juno Temple is an English actress known for her eclectic film roles and acclaimed performance as Keeley Jones in the television series "Ted Lasso."
-
E.
Carrie Coon
Carrie Coon is an American actress known for her acclaimed performances in television series like "The Leftovers" and "Fargo" as well as films such as "Gone Girl" and "The Nest."
- 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_69ad8b235e608190b5a2b1d1bfcef50b |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcc3219b881908a2f82126f9a679d |
completed | March 8, 2026, 7:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5560d5ad4819086d7c34e53afb4f6 |
completed | March 14, 2026, 12:35 p.m. |
Created at: March 8, 2026, 3:36 p.m.