Triple

T16754093
Position Surface form Disambiguated ID Type / Status
Subject Ancient Iran E407163 entity
Predicate hasPart P35 FINISHED
Object Carmania
Carmania was an ancient satrapy in southeastern Iran, known from Achaemenid and later empires for its strategic location and involvement in regional trade routes.
E1231840 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: Carmania | Statement: [Ancient Iran, hasPart, Carmania]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carmania
Context triple: [Ancient Iran, hasPart, Carmania]
  • A. Yamagumo
    Yamagumo was a Japanese Navy destroyer that served in World War II and was sunk during the Battle of Surigao Strait, part of the larger Battle of Leyte Gulf.
  • B. Otomari
    Otomari was a settlement in southern Sakhalin (then Karafuto) that served as a strategic Japanese military garrison area before and during World War II.
  • C. Mercara
    Mercara is the former anglicized name for Madikeri, a hill town and district headquarters in the Coorg (Kodagu) region of Karnataka, India.
  • D. Citura
    Citura is the public transport operator responsible for managing Reims’ urban transit network, including its tramway system, in northeastern France.
  • E. Regal Unlimited
    Regal Unlimited is a movie theater subscription service that lets members watch multiple films at Regal Cinemas for a flat monthly fee.
  • 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: Carmania
Triple: [Ancient Iran, hasPart, Carmania]
Generated description
Carmania was an ancient satrapy in southeastern Iran, known from Achaemenid and later empires for its strategic location and involvement in regional trade routes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Carmania
Target entity description: Carmania was an ancient satrapy in southeastern Iran, known from Achaemenid and later empires for its strategic location and involvement in regional trade routes.
  • A. Yamagumo
    Yamagumo was a Japanese Navy destroyer that served in World War II and was sunk during the Battle of Surigao Strait, part of the larger Battle of Leyte Gulf.
  • B. Otomari
    Otomari was a settlement in southern Sakhalin (then Karafuto) that served as a strategic Japanese military garrison area before and during World War II.
  • C. Mercara
    Mercara is the former anglicized name for Madikeri, a hill town and district headquarters in the Coorg (Kodagu) region of Karnataka, India.
  • D. Citura
    Citura is the public transport operator responsible for managing Reims’ urban transit network, including its tramway system, in northeastern France.
  • E. Regal Unlimited
    Regal Unlimited is a movie theater subscription service that lets members watch multiple films at Regal Cinemas for a flat monthly fee.
  • 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_69d8839174188190909f190097207065 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3aa28fd3c8190972e2e69ea7dece0 completed April 18, 2026, 3:58 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00a525e57881908e9e9453e6d6eb73 completed May 10, 2026, 3:32 p.m.
NEDg Description generation batch_6a00a5b3ce848190a73f06d9708bfc85 completed May 10, 2026, 3:35 p.m.
NED2 Entity disambiguation (via description) batch_6a00a6734d008190bb0a5aa28826e73a completed May 10, 2026, 3:38 p.m.
Created at: April 10, 2026, 5:21 a.m.