Triple
T5054150
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saul Bellow |
E113857
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Herzog |
E161955
|
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: Herzog | Statement: [Saul Bellow, notableWork, Herzog]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Herzog Context triple: [Saul Bellow, notableWork, Herzog]
-
A.
Herzog
chosen
Herzog is a German surname borne by numerous notable figures in politics, arts, and academia, and is also the title of a celebrated novel by Saul Bellow.
-
B.
Günther
Günther is the zoologist who first formally described the impressed tortoise species Manouria impressa.
-
C.
Günther
Günther is a German masculine given name traditionally associated with figures of Germanic origin and culture.
-
D.
Ernst
Ernst is a masculine given name of Germanic origin, commonly used in German-speaking and Scandinavian countries.
-
E.
Leopold
Leopold is a masculine given name of Germanic origin historically borne by various European rulers, saints, and notable figures.
- 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_69bd443aa1f88190abb992d138f2cf42 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd742a59448190918766c261cfa13d |
completed | March 20, 2026, 4:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bea486b394819082ea80694843b29e |
completed | March 21, 2026, 2 p.m. |
Created at: March 20, 2026, 1:38 p.m.