Triple
T36965442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James Sunderland |
E914415
|
entity |
| Predicate | receivesLetterFrom |
P4382
|
FINISHED |
| Object | Mary Shepherd-Sunderland |
—
|
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 Shepherd-Sunderland | Statement: [James Sunderland, receivesLetterFrom, Mary Shepherd-Sunderland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: receivesLetterFrom Context triple: [James Sunderland, receivesLetterFrom, Mary Shepherd-Sunderland]
-
A.
receives
chosen
Indicates that one entity is the recipient of something (such as an object, message, or action) from another entity.
-
B.
letterWrittenFrom
Indicates that a letter is authored at or sent from a particular origin location or source entity.
-
C.
letter3
Indicates that one entity is the third letter (or character) of another entity, typically a string or word.
-
D.
letterer
Indicates that one entity serves as the letterer of another, typically responsible for drawing or designing the lettering (such as text or captions) in that work.
-
E.
letters
Indicates that one entity is composed of, represented by, or associated with specific alphabetic characters or written symbols.
- F. None of above.
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_69f76e8c498c8190b2842db80aea8b3b |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcf1b3d9a08190850b388308656266 |
completed | May 7, 2026, 8:10 p.m. |
| PD | Predicate disambiguation | batch_69fcf0226d8c8190b23dceafb1794995 |
completed | May 7, 2026, 8:03 p.m. |
Created at: May 3, 2026, 4:14 p.m.