Triple

T14676424
Position Surface form Disambiguated ID Type / Status
Subject Mughan plain E344658 entity
Predicate historicallyKnownAs P20952 FINISHED
Object Mughān
Mughān is the historical name for a fertile lowland region in the South Caucasus, spanning parts of present-day Azerbaijan and Iran along the lower Kura and Aras rivers.
 E1113889 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: Mughān | Statement: [Mughan plain, historicallyKnownAs, Mughān]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mughān
Context triple: [Mughan plain, historicallyKnownAs, Mughān]
  • A. Mughniyeh
    Mughniyeh is a Lebanese family name most prominently associated with Imad Mughniyeh, a senior Hezbollah military commander.
  • B. Molazzana
    Molazzana is a small municipality in Tuscany, central Italy, known for its scenic location in the Garfagnana area of the Apennine mountains.
  • C. Makhshirin
    Makhshirin is a tractate of the Mishnah in Seder Tohorot that deals with the liquids and conditions that render foods susceptible to ritual impurity.
  • D. Marghi
    Marghi is a Chadic language spoken by the Marghi people in northeastern Nigeria.
  • E. Hasbaya
    Hasbaya is a historic town in southern Lebanon known for its strategic location near Mount Hermon and its traditional Druze and Christian communities.
  • 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: Mughān
Triple: [Mughan plain, historicallyKnownAs, Mughān]
Generated description
Mughān is the historical name for a fertile lowland region in the South Caucasus, spanning parts of present-day Azerbaijan and Iran along the lower Kura and Aras rivers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mughān
Target entity description: Mughān is the historical name for a fertile lowland region in the South Caucasus, spanning parts of present-day Azerbaijan and Iran along the lower Kura and Aras rivers.
  • A. Mughniyeh
    Mughniyeh is a Lebanese family name most prominently associated with Imad Mughniyeh, a senior Hezbollah military commander.
  • B. Molazzana
    Molazzana is a small municipality in Tuscany, central Italy, known for its scenic location in the Garfagnana area of the Apennine mountains.
  • C. Makhshirin
    Makhshirin is a tractate of the Mishnah in Seder Tohorot that deals with the liquids and conditions that render foods susceptible to ritual impurity.
  • D. Marghi
    Marghi is a Chadic language spoken by the Marghi people in northeastern Nigeria.
  • E. Hasbaya
    Hasbaya is a historic town in southern Lebanon known for its strategic location near Mount Hermon and its traditional Druze and Christian communities.
  • 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_69d822e34b348190ada4d1cdb6c7c226 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb5666e648190b5faa07076f497b8 completed April 14, 2026, 9:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fde17c24e0819089dd9606298f5ac9 completed May 8, 2026, 1:13 p.m.
NEDg Description generation batch_69fde6353dec8190b8729d61e7a2a649 completed May 8, 2026, 1:33 p.m.
NED2 Entity disambiguation (via description) batch_69fde72d93788190bd08326c3d2fea48 completed May 8, 2026, 1:37 p.m.
Created at: April 10, 2026, 1:27 a.m.