Triple

T29796659
Position Surface form Disambiguated ID Type / Status
Subject Zaječar E756568 entity
Predicate hasNearbySpa P19664 FINISHED
Object Gamzigradska Banja
Gamzigradska Banja is a Serbian spa town known for its thermal mineral springs and proximity to the archaeological site of Felix Romuliana.
 E1885363 NE FINISHED

How this triple was built (3 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: Gamzigradska Banja | Statement: [Zaječar, hasNearbySpa, Gamzigradska Banja]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Gamzigradska Banja
Triple: [Zaječar, hasNearbySpa, Gamzigradska Banja]
Generated description
Gamzigradska Banja is a Serbian spa town known for its thermal mineral springs and proximity to the archaeological site of Felix Romuliana.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: hasNearbySpa
Context triple: [Zaječar, hasNearbySpa, Gamzigradska Banja]
  • A. hasSpaService
    Indicates that an entity offers or provides spa-related services or treatments to another entity or for its use.
  • B. hasSpaTown chosen
    Indicates that a place is associated with or contains a town known for its spa or therapeutic bathing facilities.
  • C. hasSpaType
    Indicates that an entity is associated with, or classified by, a specific type or category of spa.
  • D. hasSpaResort
    Indicates that one entity possesses, includes, or is associated with a spa resort as an amenity or feature.
  • E. hasSpaStatusLocation
    Indicates that an entity has a specific spa-related status associated with a particular location.
  • F. None of above.

Provenance (6 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_69f22454583081908927516cb9938d1d completed April 29, 2026, 3:31 p.m.
NER Named-entity recognition batch_69fe68a4b67881909ca1d9f276f922e0 completed May 8, 2026, 10:50 p.m.
NED1 Entity disambiguation (via context triple) batch_6a26c90c4a448190b815f9a495063b4e completed June 8, 2026, 1:52 p.m.
NEDg Description generation batch_6a26ccffc0988190be22b829efed1b24 completed June 8, 2026, 2:09 p.m.
NED2 Entity disambiguation (via description) batch_6a26da49ea808190bba6584022192015 completed June 8, 2026, 3:05 p.m.
PD Predicate disambiguation batch_69fe680234c88190b01f953987b74972 completed May 8, 2026, 10:47 p.m.
Created at: April 29, 2026, 5:15 p.m.