Triple
T30986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gary King |
E618
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Gary King |
E618
|
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: Gary King | Statement: [Gary King, name, Gary King]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gary King Context triple: [Gary King, name, Gary King]
-
A.
Gary King
chosen
Gary King is a prominent American political scientist and quantitative methodologist at Harvard University, known for his influential work in statistical methods for social science research.
-
B.
John V. L. Hogan
John V. L. Hogan was an American radio engineer and pioneer in early radio technology and broadcasting.
-
C.
Edward S. Herman
Edward S. Herman was an American economist, media analyst, and critic of U.S. foreign policy best known for co-developing the "propaganda model" of the media.
-
D.
Neal Lane
Neal Lane is an American physicist and science policy leader who served as Director of the National Science Foundation and later as the White House Science Advisor.
-
E.
Harold T. Shapiro
Harold T. Shapiro is an economist and academic leader best known for serving as president of both Princeton University and the University of Michigan and for his influential work at the intersection of higher education and public policy.
- 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_69a2479dec388190967ba648663442c9 |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a24876ada48190b366ba8b9320ebb0 |
completed | Feb. 28, 2026, 1:44 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a255307eac81908d0055775ef3c965 |
completed | Feb. 28, 2026, 2:38 a.m. |
Created at: Feb. 28, 2026, 1:44 a.m.