Triple

T10143785
Position Surface form Disambiguated ID Type / Status
Subject Maine-et-Loire E231649 entity
Predicate contains P35 FINISHED
Object Terranjou
Terranjou is a commune in western France’s Maine-et-Loire department, known for its rural landscapes and wine-producing vineyards.
 E844686 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: Terranjou | Statement: [Maine-et-Loire, contains, Terranjou]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Terranjou
Context triple: [Maine-et-Loire, contains, Terranjou]
  • A. Kaloum
    Kaloum is the central urban commune of Conakry, Guinea, encompassing the city’s historic core, main government institutions, and port area.
  • B. Tazoult
    Tazoult is a town in northeastern Algeria known for its historical significance and proximity to the ancient Roman site of Lambaesis.
  • C. Tissi
    Tissi is a small municipality in the Sardinia region of Italy, located in the province of Sassari.
  • D. Diffa
    Diffa is a city in southeastern Niger that serves as the capital of Diffa Region and a key center for the Kanuri people near the border with Nigeria.
  • E. Rasoun
    Rasoun is a small town in northern Jordan located within the hilly, forested region of Ajloun Governorate.
  • 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: Terranjou
Triple: [Maine-et-Loire, contains, Terranjou]
Generated description
Terranjou is a commune in western France’s Maine-et-Loire department, known for its rural landscapes and wine-producing vineyards.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Terranjou
Target entity description: Terranjou is a commune in western France’s Maine-et-Loire department, known for its rural landscapes and wine-producing vineyards.
  • A. Kaloum
    Kaloum is the central urban commune of Conakry, Guinea, encompassing the city’s historic core, main government institutions, and port area.
  • B. Tazoult
    Tazoult is a town in northeastern Algeria known for its historical significance and proximity to the ancient Roman site of Lambaesis.
  • C. Tissi
    Tissi is a small municipality in the Sardinia region of Italy, located in the province of Sassari.
  • D. Diffa
    Diffa is a city in southeastern Niger that serves as the capital of Diffa Region and a key center for the Kanuri people near the border with Nigeria.
  • E. Rasoun
    Rasoun is a small town in northern Jordan located within the hilly, forested region of Ajloun Governorate.
  • 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_69ca848364f881908a24366a6feec1db completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cdeb28a1708190b46499dbe51a694a completed April 2, 2026, 4:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2e618b0bc8190bc1d6f15dac2708e completed April 5, 2026, 10:45 p.m.
NEDg Description generation batch_69d2e866cc4881909b5f4d1502a69885 completed April 5, 2026, 10:55 p.m.
NED2 Entity disambiguation (via description) batch_69d2e91061248190a7f9022c26daba0e completed April 5, 2026, 10:58 p.m.
Created at: March 30, 2026, 9:07 p.m.