Triple
T22231884
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | On Raglan Road |
E549486
|
entity |
| Predicate | notablePerformer |
P17435
|
FINISHED |
| Object | Mary Black |
—
|
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: Mary Black | Statement: [On Raglan Road, notablePerformer, Mary Black]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Black Context triple: [On Raglan Road, notablePerformer, Mary Black]
-
A.
Mary Black
chosen
Mary Black is an acclaimed Irish folk singer known for her influential solo career and interpretations of traditional and contemporary songs.
-
B.
Mary Black
Mary Black is the mother of William King, known primarily in relation to him.
-
C.
Mary Blackmore
Mary Blackmore was the mother of English novelist Richard Doddridge Blackmore, best known for writing the classic romance "Lorna Doone."
-
D.
Mary Ann Black
Mary Ann Black was the wife of English footballer and later prominent judge and politician Stanley Matthews.
-
E.
Mary Shepherd
Mary Shepherd was a British philosopher known for her early 19th-century work on causation and metaphysics, which challenged the ideas of David Hume.
- 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_69e11e4102b881909cf47d3768e25c19 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12bf3de648190986a734f19643a8c |
completed | April 28, 2026, 9:51 p.m. |
Created at: April 16, 2026, 8:38 p.m.