Triple
T16899361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Сентандреја |
E424392
|
entity |
| Predicate | историјскиПовезанСа |
P16345
|
FINISHED |
| Object | Срби у Мађарској |
—
|
LITERAL 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: Срби у Мађарској | Statement: [Сентандреја, историјскиПовезанСа, Срби у Мађарској]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: историјскиПовезанСа Context triple: [Сентандреја, историјскиПовезанСа, Срби у Мађарској]
-
A.
historicallyLinked
chosen
Indicates that two entities are connected through a shared or related historical event, period, or development.
-
B.
historicalSee
Indicates that one entity observed, encountered, or took visual notice of another entity in the past.
-
C.
historical
Indicates that the subject has existed, occurred, or been relevant in the past rather than in the present or future.
-
D.
historicallyIn
Indicates that one entity existed, occurred, or was situated within the historical context, period, or jurisdiction associated with another entity.
-
E.
otherHistoricSee
Indicates that an entity is associated with or linked to another historically significant site, event, or point of interest that can be seen or visited.
- F. None of above.
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_69d889da3e8c8190a2b118f383f0beac |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e3c8da7b0481909111358871875023 |
completed | April 18, 2026, 6:09 p.m. |
| PD | Predicate disambiguation | batch_69e32b9489408190bcb2ede567ff5bf9 |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:29 a.m.