Triple

T33575642
Position Surface form Disambiguated ID Type / Status
Subject Waterloo E860022 entity
Predicate hasVersion P455 FINISHED
Object Waterloo (Swedish-language version)
Waterloo (Swedish-language version) is the original Swedish recording of ABBA’s hit song “Waterloo,” released in 1974 alongside its more internationally known English-language version.
E2058135 NE 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: Waterloo (Swedish-language version) | Statement: [Waterloo, hasVersion, Waterloo (Swedish-language version)]
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: Waterloo (Swedish-language version)
Triple: [Waterloo, hasVersion, Waterloo (Swedish-language version)]
Generated description
Waterloo (Swedish-language version) is the original Swedish recording of ABBA’s hit song “Waterloo,” released in 1974 alongside its more internationally known English-language version.

Provenance (5 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_69f3497d37848190afcbb5ef3f5c7376 completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69f6f74b95248190a3546b33dda2402d completed May 3, 2026, 7:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a35afdf32948190b11081d8a81b61fd completed June 19, 2026, 9:08 p.m.
NEDg Description generation batch_6a35b7e47a3c81908599f78ac02c2320 completed June 19, 2026, 9:43 p.m.
NED2 Entity disambiguation (via description) batch_6a35b877a9348190ab14359362f58d80 completed June 19, 2026, 9:45 p.m.
Created at: May 1, 2026, 1:40 a.m.