Triple
T21022074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Beverly Shea |
E517834
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Shea |
—
|
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: Shea | Statement: [George Beverly Shea, familyName, Shea]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shea Context triple: [George Beverly Shea, familyName, Shea]
-
A.
Shea
chosen
Shea is the family name of American violinist Scarlet Rivera, known for her collaborations with Bob Dylan.
-
B.
Shea
Shea is a given name most notably associated with Canadian former professional ice hockey defenseman Shea Weber.
-
C.
Madi
Madi is a character portrayed by American actress Lexi Underwood, known for her work in television and film.
-
D.
Madi
Madi is a Central Sudanic language spoken primarily by the Madi people in parts of South Sudan and northern Uganda.
-
E.
Madi
Madi is a town in Nepal’s Chitwan District known for its rural setting near Chitwan National Park and its agriculture-based local economy.
- 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_69e0b50262b081909bc488937145eb73 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc5e85d08190a67956a3dbe693de |
completed | April 21, 2026, 4:26 a.m. |
Created at: April 16, 2026, 1:54 p.m.