Triple
T22936242
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Meredith Black |
E569590
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object | Henry 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: Henry Black | Statement: [Meredith Black, hasChild, Henry Black]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Henry Black Context triple: [Meredith Black, hasChild, Henry Black]
-
A.
Henry Black
chosen
Henry Black was the son of prominent American jurist and U.S. Attorney General Jeremiah Sullivan Black.
-
B.
Henry Black
Henry Black was an American legal scholar best known for compiling influential legal reports and reference works, including the Black Reports.
-
C.
Henry Baldwin
Henry Baldwin was an Associate Justice of the U.S. Supreme Court in the early 19th century, known for his often idiosyncratic and independent judicial opinions.
-
D.
Arthur Blacket
Arthur Blacket was an Australian architect and the son of prominent colonial architect Edmund Blacket.
-
E.
Walter Blackie
Walter Blackie was a Scottish publisher and businessman best known as the client for Charles Rennie Mackintosh’s iconic Hill House in Helensburgh.
- 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_69e24590862c8190858f180ad302adab |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1813608e48190922df7a5386dc391 |
completed | April 29, 2026, 3:55 a.m. |
Created at: April 17, 2026, 3:44 p.m.