Triple
T17967849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harmon |
E449258
|
entity |
| Predicate | relatedSurname |
P13741
|
FINISHED |
| Object | Herman |
—
|
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: Herman | Statement: [Harmon, relatedSurname, Herman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Herman Context triple: [Harmon, relatedSurname, Herman]
-
A.
Herman
chosen
Herman is a surname most notably associated with Edward S. Herman, an American economist, media analyst, and critic of U.S. foreign policy.
-
B.
Herman
Herman is the given name of Belgian politician Herman De Croo, a long-serving liberal statesman and former President of the Belgian Chamber of Representatives.
-
C.
Herman
Herman is the middle name of legendary American baseball player Babe Ruth, whose full name was George Herman Ruth Jr.
-
D.
Herman
Herman is the given first name of the American blues singer and harmonica player Junior Parker.
-
E.
Herman
Herman is a masculine given name of Germanic origin commonly used in Dutch, German, and Scandinavian contexts.
- 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_69d8b9f9927c8190a006110c8b996e61 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b13935908190b5269a84a3df2460 |
completed | April 19, 2026, 10:40 a.m. |
Created at: April 10, 2026, 10:22 a.m.