Triple
T22464648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maisie Lockwood |
E555318
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Eli Mills |
—
|
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: Eli Mills | Statement: [Maisie Lockwood, associatedWith, Eli Mills]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eli Mills Context triple: [Maisie Lockwood, associatedWith, Eli Mills]
-
A.
Eli Mills
chosen
Eli Mills is a primary antagonist in the Jurassic World film series, known as a manipulative businessman who exploits dinosaurs for profit.
-
B.
Jeremy Miller
Jeremy Miller is an American actor best known for playing Ben Seaver on the 1980s sitcom "Growing Pains."
-
C.
Jake Miller
Jake Miller is an actor known for appearing in the independent drama film "Paranoid Park," directed by Gus Van Sant.
-
D.
Logan Miller
Logan Miller is an American actor known for his roles in films such as "Before I Fall" and various television series.
-
E.
Ryan Meili
Ryan Meili is a Canadian physician and politician who served as leader of the Saskatchewan New Democratic Party and leader of the opposition in Saskatchewan.
- 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_69e11e51fdec8190adfdf9f8a6362221 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b82549c8190943c0940bb90bafc |
completed | April 29, 2026, 1:14 a.m. |
Created at: April 16, 2026, 8:48 p.m.