Triple

T18208606
Position Surface form Disambiguated ID Type / Status
Subject Zhibiani E435969 entity
Predicate near P350 FINISHED
Object Murkmeli
Murkmeli is a village in the mountainous Svaneti region of northwestern Georgia, known for its traditional Svan towers and historic highland architecture.
 E1312839 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: Murkmeli | Statement: [Zhibiani, near, Murkmeli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Murkmeli
Context triple: [Zhibiani, near, Murkmeli]
  • A. Darkside
    Darkside is a track by the American funeral doom metal band Funeral, known for its slow, heavy atmosphere and melancholic tone.
  • B. Blacker
    Blacker is a comparative form of the color term "black," indicating a greater degree of darkness or blackness.
  • C. Hintere Schwärze
    Hintere Schwärze is a prominent high Alpine peak in the Ötztal Alps on the Austria–Italy border, popular with experienced mountaineers and ski tourers.
  • D. Mud
    Mud is a 2012 American drama film directed by Jeff Nichols, in which Matthew McConaughey plays a fugitive who befriends two boys on the Mississippi River.
  • E. Mud
    Mud is a work created by Sarah Green, likely a notable piece in her artistic or literary portfolio.
  • 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: Murkmeli
Triple: [Zhibiani, near, Murkmeli]
Generated description
Murkmeli is a village in the mountainous Svaneti region of northwestern Georgia, known for its traditional Svan towers and historic highland architecture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Murkmeli
Target entity description: Murkmeli is a village in the mountainous Svaneti region of northwestern Georgia, known for its traditional Svan towers and historic highland architecture.
  • A. Darkside
    Darkside is a track by the American funeral doom metal band Funeral, known for its slow, heavy atmosphere and melancholic tone.
  • B. Blacker
    Blacker is a comparative form of the color term "black," indicating a greater degree of darkness or blackness.
  • C. Hintere Schwärze
    Hintere Schwärze is a prominent high Alpine peak in the Ötztal Alps on the Austria–Italy border, popular with experienced mountaineers and ski tourers.
  • D. Mud
    Mud is a 2012 American drama film directed by Jeff Nichols, in which Matthew McConaughey plays a fugitive who befriends two boys on the Mississippi River.
  • E. Mud
    Mud is a work created by Sarah Green, likely a notable piece in her artistic or literary portfolio.
  • 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_69d8b90dba6481908e119eb9aa4ca0cb completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e2261a848190b62a8485009f8f38 completed April 19, 2026, 2:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a039f128840819096b0090350a6de85 completed May 12, 2026, 9:43 p.m.
NEDg Description generation batch_6a039f8aa3ac8190baa85cbad12233fb completed May 12, 2026, 9:45 p.m.
NED2 Entity disambiguation (via description) batch_6a03a0a4ef148190b6c69f72f019964a completed May 12, 2026, 9:50 p.m.
Created at: April 10, 2026, 10:32 a.m.