Triple

T15312419
Position Surface form Disambiguated ID Type / Status
Subject Constance Wu E366069 entity
Predicate appearedIn P795 FINISHED
Object Parallels
Parallels is a science fiction film about a group of people who discover a mysterious building that serves as a gateway to parallel Earths.
E1150760 NE FINISHED

How this triple was built (4 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: Parallels | Statement: [Constance Wu, appearedIn, Parallels]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Parallels
Context triple: [Constance Wu, appearedIn, Parallels]
  • A. Parallels
    "Parallels" is a progressive rock song by the English band Yes, featured on their 1977 album *Going for the One*.
  • B. Parallels Desktop
    Parallels Desktop is a virtualization software for macOS that allows users to run Windows and other operating systems alongside macOS applications.
  • C. VMware Fusion
    VMware Fusion is a virtualization software application for macOS that allows users to run Windows and other operating systems alongside Mac applications on the same machine.
  • D. Xen
    Xen is a mysterious, floating borderworld of alien ecosystems and strange physics that serves as a pivotal interdimensional realm in the Half-Life series.
  • E. Xen
    Xen is an open-source type-1 hypervisor that enables efficient virtualization of multiple operating systems on the same physical hardware.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Parallels
Triple: [Constance Wu, appearedIn, Parallels]
Generated description
Parallels is a science fiction film about a group of people who discover a mysterious building that serves as a gateway to parallel Earths.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Parallels
Target entity description: Parallels is a science fiction film about a group of people who discover a mysterious building that serves as a gateway to parallel Earths.
  • A. Parallels
    "Parallels" is a progressive rock song by the English band Yes, featured on their 1977 album *Going for the One*.
  • B. Parallels Desktop
    Parallels Desktop is a virtualization software for macOS that allows users to run Windows and other operating systems alongside macOS applications.
  • C. VMware Fusion
    VMware Fusion is a virtualization software application for macOS that allows users to run Windows and other operating systems alongside Mac applications on the same machine.
  • D. Xen
    Xen is an open-source type-1 hypervisor that enables efficient virtualization of multiple operating systems on the same physical hardware.
  • E. Xen
    Xen is a mysterious, floating borderworld of alien ecosystems and strange physics that serves as a pivotal interdimensional realm in the Half-Life series.
  • F. None of above. chosen

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_69d85a113ee881908e297a1d38dd79fa completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03cd2d5a88190aead748920f93d47 completed April 16, 2026, 1:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69fef8a3da3881909b50cfbec0543adc completed May 9, 2026, 9:04 a.m.
NEDg Description generation batch_69fefdb82b2081908084a12a58ad3477 completed May 9, 2026, 9:26 a.m.
NED2 Entity disambiguation (via description) batch_69fefe6c42708190bd893885fc5bc88e completed May 9, 2026, 9:29 a.m.
Created at: April 10, 2026, 3:16 a.m.