Triple
T9046296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Béla Tarr |
E216763
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Béla |
E383704
|
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: Béla | Statement: [Béla Tarr, givenName, Béla]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Béla Context triple: [Béla Tarr, givenName, Béla]
-
A.
Béla
chosen
Béla was a common medieval Hungarian royal given name borne by several kings, most notably Béla IV of Hungary.
-
B.
Lajos
Lajos is a Hungarian masculine given name commonly used in Central and Eastern Europe.
-
C.
György
György is a Hungarian given name commonly used for men, equivalent to the English name George.
-
D.
András
András is the Hungarian given name of Andrew S. Grove, the influential former CEO and co-founder of Intel.
-
E.
Géza
Géza was a 10th-century Grand Prince of the Hungarians who played a key role in consolidating the Hungarian state and paving the way for its Christianization under his son Stephen I.
- 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_69ca83d22d488190adbce5e020e9cd1d |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc6b4e4b888190a425e29b193b506f |
completed | April 1, 2026, 12:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0e3017a7c8190a7182acc7831d09b |
completed | April 4, 2026, 10:08 a.m. |
Created at: March 30, 2026, 7:09 p.m.