Triple
T10311434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth Perkins |
E241898
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Big |
E62646
|
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: Big | Statement: [Elizabeth Perkins, notableWork, Big]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Big Context triple: [Elizabeth Perkins, notableWork, Big]
-
A.
Big
chosen
Big is a 1988 fantasy-comedy film in which Tom Hanks plays a boy who magically becomes an adult overnight, earning widespread acclaim and helping establish him as a major Hollywood star.
-
B.
Groß
Groß is a German surname most notably borne by the influential Dadaist and New Objectivity painter and caricaturist George Grosz.
-
C.
Grand
Grand is a Chicago 'L' rapid transit station on the CTA Blue Line serving the city's downtown area.
-
D.
Grand
Grand is a Chicago 'L' rapid transit station on the Red Line located in the city's Near North Side.
-
E.
Bigger
"Bigger" is a comedy television series created and produced by filmmaker Will Packer that follows a group of friends navigating love, careers, and ambitions in Atlanta.
- 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_69d381ac38808190a8ca7457c85b625b |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d32ac6c08190b23eb042b3ec284a |
completed | April 7, 2026, 9:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d7502f7b308190aaefd62f2f8a0ac3 |
completed | April 9, 2026, 7:07 a.m. |
Created at: April 6, 2026, 11:47 a.m.