Triple

T22494005
Position Surface form Disambiguated ID Type / Status
Subject Hubert Burda Media E556091 entity
Predicate owns P347 FINISHED
Object XING 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: XING | Statement: [Hubert Burda Media, owns, XING]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: XING
Context triple: [Hubert Burda Media, owns, XING]
  • A. Naver Contacts
    Naver Contacts is Naver’s cloud-based address book service that manages and syncs users’ contact information across Naver’s apps and devices.
  • B. EXALEAD
    EXALEAD is an enterprise search and information access software brand known for its advanced search, indexing, and data discovery solutions.
  • C. Namedropper
    Namedropper is a semi-autobiographical coming-of-age novel by British writer Emma Forrest, known for its sharp, witty portrayal of a teenage girl's emotional turmoil and relationships.
  • D. People Nation
    People Nation is a large Chicago-based street gang alliance formed in the late 1970s that unites various affiliated gangs under a common structure, symbols, and rivalries.
  • E. Xing chosen
    Xing is a German-based professional networking platform focused on career development and business connections, particularly in German-speaking countries.
  • 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_69e11e5445bc8190b6a9481926db3355 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15cb0dfb88190a4175e5e95d7ad4b completed April 29, 2026, 1:19 a.m.
Created at: April 16, 2026, 8:49 p.m.