Triple
T22490140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hristo Stoichkov |
E555992
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Stoichkov |
—
|
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: Stoichkov | Statement: [Hristo Stoichkov, familyName, Stoichkov]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stoichkov Context triple: [Hristo Stoichkov, familyName, Stoichkov]
-
A.
Stoichkov
chosen
Stoichkov is a Bulgarian surname most famously associated with Hristo Stoichkov, the legendary footballer and Ballon d'Or winner.
-
B.
Stoyko
Stoyko is the given name of Ilarion Makariopolski, a notable Bulgarian cleric and national revival figure.
-
C.
Dimitar
Dimitar is a masculine given name of Slavic origin, commonly used in Bulgaria and other Eastern European countries.
-
D.
Andre Stojka
Andre Stojka is an American voice actor known for his work in animated films, television series, and video games, including roles in various Disney productions.
-
E.
Veselin Stoyanov
Veselin Stoyanov is a computer scientist and researcher known for his work in natural language processing and machine learning.
- 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_69e11e53897c819088863779f8c50bb0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15c40930c81908310ac6afd98c62e |
completed | April 29, 2026, 1:17 a.m. |
Created at: April 16, 2026, 8:49 p.m.