Triple

T1004544
Position Surface form Disambiguated ID Type / Status
Subject Tower of London E21679 entity
Predicate hasPart P35 FINISHED
Object White Tower
The White Tower is the central Norman keep of the Tower of London, historically serving as a royal residence, fortress, and symbol of royal authority.
E117902 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: White Tower | Statement: [Tower of London, hasPart, White Tower]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: White Tower
Context triple: [Tower of London, hasPart, White Tower]
  • A. White Tower
    The White Tower is a prominent Renaissance-era bell tower and landmark in the historic center of Hradec Králové in the Czech Republic.
  • B. City of Dreaming Spires
    City of Dreaming Spires is a poetic nickname for Oxford, England, evoking its skyline of historic university towers and spires.
  • C. City of a Hundred Spires
    City of a Hundred Spires is a poetic nickname for Prague, highlighting its skyline filled with historic church towers and spires.
  • D. Red Tower
    Red Tower is a historic medieval tower and landmark in the German city of Chemnitz.
  • E. The Castle
    The Castle is a surreal, unfinished novel by Franz Kafka that follows a land surveyor’s futile attempts to gain access to a mysterious, bureaucratic authority that governs a remote village.
  • 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: White Tower
Triple: [Tower of London, hasPart, White Tower]
Generated description
The White Tower is the central Norman keep of the Tower of London, historically serving as a royal residence, fortress, and symbol of royal authority.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: White Tower
Target entity description: The White Tower is the central Norman keep of the Tower of London, historically serving as a royal residence, fortress, and symbol of royal authority.
  • A. White Tower
    The White Tower is a prominent Renaissance-era bell tower and landmark in the historic center of Hradec Králové in the Czech Republic.
  • B. City of Dreaming Spires
    City of Dreaming Spires is a poetic nickname for Oxford, England, evoking its skyline of historic university towers and spires.
  • C. City of a Hundred Spires
    City of a Hundred Spires is a poetic nickname for Prague, highlighting its skyline filled with historic church towers and spires.
  • D. Red Tower
    Red Tower is a historic medieval tower and landmark in the German city of Chemnitz.
  • E. The Castle
    The Castle is the iconic red sandstone building on the National Mall in Washington, D.C., that serves as the historic headquarters and visitor center of the Smithsonian Institution.
  • 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_69a493c53e648190ae8cb76c433fd9a7 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b4ff614081909478500ada1f5059 completed March 1, 2026, 9:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac2a1ecddc8190b954d16c6e269498 completed March 7, 2026, 1:37 p.m.
NEDg Description generation batch_69ac2a8dd818819088e6140e9a12594b completed March 7, 2026, 1:39 p.m.
NED2 Entity disambiguation (via description) batch_69ac2af2efd88190b1da673aa3ead5fd completed March 7, 2026, 1:41 p.m.
Created at: March 1, 2026, 7:41 p.m.