Triple
T20586196
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Poppins |
E505793
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Matthew Garber |
—
|
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: Matthew Garber | Statement: [Mary Poppins, starring, Matthew Garber]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matthew Garber Context triple: [Mary Poppins, starring, Matthew Garber]
-
A.
Matthew Garber
chosen
Matthew Garber was a British child actor best known for playing Michael Banks in Disney’s classic film "Mary Poppins" (1964).
-
B.
Spencer Laudiero
Spencer Laudiero is an American animation director and storyboard artist known for his work on television series such as "Family Guy" and "The Orville."
-
C.
Drew Ballinger
Drew Ballinger is a fictional character from the 1972 film "Deliverance," known as one of the four men whose canoe trip in rural Georgia turns into a harrowing fight for survival.
-
D.
Adam Kimmel
Adam Kimmel is an American cinematographer known for his work on acclaimed films such as "Capote," "Lars and the Real Girl," and "Never Let Me Go."
-
E.
Matthew Stuecken
Matthew Stuecken is a film screenwriter best known for co-writing the psychological sci-fi thriller "10 Cloverfield Lane."
- 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_69e0b4b9669c8190b8e81fc72817d42c |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a976bca4819086a4949e299159b5 |
completed | April 20, 2026, 10:32 p.m. |
Created at: April 16, 2026, 11:40 a.m.