Triple
T6528550
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harry Edwards |
E151367
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Harry Edwards |
E151367
|
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: Harry Edwards | Statement: [Harry Edwards, name, Harry Edwards]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harry Edwards Context triple: [Harry Edwards, name, Harry Edwards]
-
A.
Harry Edwards
chosen
Harry Edwards is an American sociologist and civil rights activist best known for his work on race and sports, including his role in organizing the 1968 Olympic Project for Human Rights.
-
B.
Harry D. Edwards
Harry D. Edwards was an American film director active during the silent and early sound eras, known for his work on comedy shorts and features.
-
C.
James Coleman
James Coleman was an influential American sociologist known for his work on social theory, education, and the development of rational choice approaches in sociology.
-
D.
James Coleman
James Coleman is a physicist and engineer known for his work in semiconductor lasers and optoelectronics.
-
E.
Robert Hicks
Robert Hicks is a name shared by several notable individuals, including authors, politicians, and professionals across various fields.
- 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_69c687f522748190b3058405553cdabd |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6ada9c8408190b1bc327985366be9 |
completed | March 27, 2026, 4:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6d52ca9988190addfdae6d7b53a6e |
completed | March 27, 2026, 7:06 p.m. |
Created at: March 27, 2026, 1:46 p.m.