Triple
T17430183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lance Berkman |
E423848
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Berkman |
—
|
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: Berkman | Statement: [Lance Berkman, familyName, Berkman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Berkman Context triple: [Lance Berkman, familyName, Berkman]
-
A.
Berkman
chosen
Berkman is a surname most prominently associated with former Major League Baseball All-Star Lance Berkman.
-
B.
Kogod
Kogod is the business school of American University in Washington, D.C., offering undergraduate and graduate programs in business and management.
-
C.
Belfer
Belfer is a surname most prominently associated with American businessman and philanthropist Robert A. Belfer.
-
D.
Berk
Berk is a Turkish surname shared by various individuals, including the notable poet İlhan Berk.
-
E.
Berk
Berk is the remote Viking island village that serves as the primary setting in the How to Train Your Dragon franchise.
- 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_69d889d88b6081908bada047f5b3ba51 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e448ffb9c8819099fabfeebdc06883 |
completed | April 19, 2026, 3:16 a.m. |
Created at: April 10, 2026, 5:46 a.m.