Triple
T20474986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Ashley Sunday |
E502290
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Helen Sunday |
—
|
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: Helen Sunday | Statement: [William Ashley Sunday, child, Helen Sunday]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Helen Sunday Context triple: [William Ashley Sunday, child, Helen Sunday]
-
A.
Helen Sunday
chosen
Helen Sunday was the daughter of famed American evangelist and former baseball player Billy Sunday.
-
B.
Helen Morris
Helen Morris is an American book editor and the longtime wife of acclaimed film director Martin Scorsese.
-
C.
Helen Davies
Helen Davies was the first wife of American actor George Peppard, with whom she was married in the 1950s and early 1960s.
-
D.
Helen Cammock
Helen Cammock is a British artist known for her multidisciplinary practice exploring history, memory, and social justice, and for being a joint winner of the Turner Prize.
-
E.
Helen Gardiner
Helen Gardiner was a Canadian art collector and philanthropist best known for co-founding Toronto’s Gardiner Museum of ceramic art.
- 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_69e0b4ae5f1081908768b0c9a3a0bf38 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6996464448190bdf9cf63c736d6dd |
completed | April 20, 2026, 9:23 p.m. |
Created at: April 16, 2026, 11:34 a.m.