Triple
T23820118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Szereda |
E589208
|
entity |
| Predicate | hasOfficialCounterpart |
P6587
|
FINISHED |
| Object | Miercurea Ciuc |
—
|
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: Miercurea Ciuc | Statement: [Szereda, hasOfficialCounterpart, Miercurea Ciuc]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOfficialCounterpart Context triple: [Szereda, hasOfficialCounterpart, Miercurea Ciuc]
-
A.
hasCounterpart
chosen
Indicates that one entity corresponds to, matches, or serves as an equivalent or parallel version of another entity.
-
B.
hasCounterpartName
Indicates that an entity has an alternative or corresponding name used as its counterpart in another context, system, or representation.
-
C.
hasSmallerCounterpart
Indicates that one entity has another entity as its corresponding version that is smaller in size, scale, or magnitude.
-
D.
hasCounterpartNameLanguage
Indicates that an entity’s counterpart (e.g., in another context or system) has a name expressed in a specified language.
-
E.
hasCounterpartNickname
Indicates that one entity is used as an alternative or counterpart nickname for another entity.
- 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_69e25d18619081909c7fb89d8926f14a |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c7ae4f8c8190a92621861cbae2f4 |
completed | April 29, 2026, 8:56 a.m. |
| PD | Predicate disambiguation | batch_69f156036ad48190bc2ffdaf39218bcb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:59 p.m.