Triple
T5292620
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clark |
E119775
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Clarke |
E73353
|
NE FINISHED |
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: Clarke | Statement: [Clark, hasVariant, Clarke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Clarke Context triple: [Clark, hasVariant, Clarke]
-
A.
Clarke
chosen
Clarke is a common English and Irish surname historically associated with the occupation of a clerk or scholar.
-
B.
Hadley
Hadley is a given name most notably borne by Hadley Richardson, the first wife of writer Ernest Hemingway.
-
C.
Tuthill
Tuthill is a surname most notably associated with William Burnet Tuthill, the American architect who designed Carnegie Hall in New York City.
-
D.
Risley
Risley is a village in Derbyshire, England, known for its historic buildings and rural character near the town of Sandiacre.
-
E.
Dunlap
Dunlap is a residential neighborhood in Seattle’s Rainier Valley known for its diverse community and proximity to Lake Washington.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd446de5648190b313a90bd96730d2 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd84eec0c081908da5fad1b1fff9d6 |
completed | March 20, 2026, 5:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf06f3c7508190be98e08cef130a4d |
completed | March 21, 2026, 9 p.m. |
Created at: March 20, 2026, 1:52 p.m.