Triple
T17631714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sándor Márai |
E429991
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Sándor |
—
|
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: Sándor | Statement: [Sándor Márai, givenName, Sándor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sándor Context triple: [Sándor Márai, givenName, Sándor]
-
A.
Sándor
chosen
Sándor is a Hungarian given name, traditionally used as the local form of Alexander.
-
B.
András
András is the Hungarian given name of Andrew S. Grove, the influential former CEO and co-founder of Intel.
-
C.
Márton
Márton is a Hungarian given name, equivalent to the name Martin in other languages.
-
D.
Zoltán
Zoltán was an early medieval Hungarian ruler, traditionally regarded as one of the first princes of the Principality of Hungary and a successor in the Árpád dynasty.
-
E.
Béla
Béla was a common medieval Hungarian royal given name borne by several kings, most notably Béla IV of Hungary.
- 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_69d889e37f308190a6aa0a69daff86c7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46dc192dc8190854f1fe5d5ed696a |
completed | April 19, 2026, 5:53 a.m. |
Created at: April 10, 2026, 5:52 a.m.