Triple

T20114607
Position Surface form Disambiguated ID Type / Status
Subject Venera 11 E490423 entity
Predicate successor P78 FINISHED
Object Venera 12 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: Venera 12 | Statement: [Venera 11, successor, Venera 12]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Venera 12
Context triple: [Venera 11, successor, Venera 12]
  • A. Venera 12 chosen
    Venera 12 was a Soviet space probe launched in 1978 as part of the Venera program to study Venus’s atmosphere and surface.
  • B. Venera 11
    Venera 11 was a Soviet space probe launched in 1978 as part of the Venera program to study Venus’s atmosphere and surface.
  • C. Venera 13
    Venera 13 was a Soviet space probe that successfully landed on Venus in 1982, transmitting the first color images and extensive data from the planet’s surface.
  • D. Venera 14
    Venera 14 was a Soviet space probe launched in 1981 that successfully landed on Venus, conducting experiments and transmitting data and images from the planet’s surface.
  • E. Venera 10
    Venera 10 was a Soviet space probe that successfully orbited Venus and transmitted data from its surface as part of the USSR’s pioneering Venera program.
  • 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_69da62636cc08190982cc71733a17b8d completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e666e3f2288190840d1eb431ac9a1b completed April 20, 2026, 5:48 p.m.
Created at: April 11, 2026, 11:29 p.m.