Triple

T6608110
Position Surface form Disambiguated ID Type / Status
Subject Dock10 E149168 entity
Predicate hasStudio P30541 FINISHED
Object HQ10
HQ10 is a television production studio facility that forms part of Dock10’s media and broadcast complex in Salford, UK.
 E606845 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: HQ10 | Statement: [Dock10, hasStudio, HQ10]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HQ10
Context triple: [Dock10, hasStudio, HQ10]
  • A. D10
    D10 is the station code for Deanwood, a stop on Washington, D.C.’s Metrorail system.
  • B. T10
    T10 is a technical committee under INCITS responsible for developing standards for SCSI (Small Computer System Interface) and related storage interfaces.
  • C. J100
    J100 is the internal model code used by Lexus to designate the second generation of its full-size luxury SUV, the Lexus LX.
  • D. QH
    QH is the standard abbreviation for Qinghai, a large inland province in northwestern China known for the Qinghai-Tibet Plateau and Qinghai Lake.
  • E. CQ
    CQ is a 2001 independent film directed by Roman Coppola that blends retro-futuristic sci-fi and personal drama in a stylized homage to 1960s European cinema.
  • 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: HQ10
Triple: [Dock10, hasStudio, HQ10]
Generated description
HQ10 is a television production studio facility that forms part of Dock10’s media and broadcast complex in Salford, UK.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HQ10
Target entity description: HQ10 is a television production studio facility that forms part of Dock10’s media and broadcast complex in Salford, UK.
  • A. D10
    D10 is the station code for Deanwood, a stop on Washington, D.C.’s Metrorail system.
  • B. T10
    T10 is a technical committee under INCITS responsible for developing standards for SCSI (Small Computer System Interface) and related storage interfaces.
  • C. J100
    J100 is the internal model code used by Lexus to designate the second generation of its full-size luxury SUV, the Lexus LX.
  • D. QH
    QH is the standard abbreviation for Qinghai, a large inland province in northwestern China known for the Qinghai-Tibet Plateau and Qinghai Lake.
  • E. CQ
    CQ is a 2001 independent film directed by Roman Coppola that blends retro-futuristic sci-fi and personal drama in a stylized homage to 1960s European cinema.
  • 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_69c687eaa7508190bb58ce2aa02039b3 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6af31c4748190ab5027771c9ce5b2 completed March 27, 2026, 4:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6e43cc42081909762eec710773f40 completed March 27, 2026, 8:10 p.m.
NEDg Description generation batch_69c6e57d71ec8190b79615f11eadec26 completed March 27, 2026, 8:15 p.m.
NED2 Entity disambiguation (via description) batch_69c6e614f04c8190b25b553553895799 completed March 27, 2026, 8:18 p.m.
Created at: March 27, 2026, 1:57 p.m.