Triple

T10391337
Position Surface form Disambiguated ID Type / Status
Subject Batman: Arkham Asylum E244898 entity
Predicate platform P1292 FINISHED
Object OnLive E440657 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: OnLive | Statement: [Batman: Arkham Asylum, platform, OnLive]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: OnLive
Context triple: [Batman: Arkham Asylum, platform, OnLive]
  • A. OnLive chosen
    OnLive was a pioneering but ultimately short-lived cloud gaming service that streamed high-end video games over the internet to low-powered devices.
  • B. Nvidia GeForce Now
    Nvidia GeForce Now is a cloud gaming service that streams PC games from remote servers to various devices, allowing users to play high-end titles without powerful local hardware.
  • C. Google Stadia
    Google Stadia was a cloud gaming service by Google that allowed users to stream and play video games over the internet without dedicated gaming hardware.
  • D. Xbox Cloud Gaming
    Xbox Cloud Gaming is Microsoft’s cloud-based game streaming service that lets users play Xbox titles on various devices without needing a physical console.
  • E. Ouya
    Ouya was a low-cost, Android-based microconsole released in 2013 that focused on downloadable indie games and was funded through a highly publicized Kickstarter campaign.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d381b5116081908d85227bab6d3c0c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e9b5b43081908641a5abfb08dc2b completed April 7, 2026, 11:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69d795b9974c819087340adc3622279e completed April 9, 2026, 12:04 p.m.
Created at: April 6, 2026, 12:06 p.m.