Triple

T16451901
Position Surface form Disambiguated ID Type / Status
Subject Regio IV Samnium E399571 entity
Predicate contains P35 FINISHED
Object Compsa
Compsa was an ancient town in the Samnium region of southern Italy, historically notable for its strategic location and role in Roman-era conflicts.
 E1213990 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: Compsa | Statement: [Regio IV Samnium, contains, Compsa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Compsa
Context triple: [Regio IV Samnium, contains, Compsa]
  • A. Comeng
    Comeng is an Australian engineering and rolling stock manufacturing company best known for producing trains and other rail vehicles used across the country.
  • B. Cortalim
    Cortalim is a village in South Goa, India, known for its scenic riverside location, historic churches, and role as a transport hub near the Zuari River.
  • C. Sogeti
    Sogeti is a professional services and technology consulting company specializing in IT and engineering solutions, operating as a subsidiary of Capgemini.
  • D. Compans
    Compans is a small French commune located in the Seine-et-Marne department in the Île-de-France region, northeast of Paris.
  • E. Kompa
    Kompa is a popular Haitian dance music genre known for its smooth, guitar-driven rhythms and strong influence on Caribbean and diasporic music styles.
  • 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: Compsa
Triple: [Regio IV Samnium, contains, Compsa]
Generated description
Compsa was an ancient town in the Samnium region of southern Italy, historically notable for its strategic location and role in Roman-era conflicts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Compsa
Target entity description: Compsa was an ancient town in the Samnium region of southern Italy, historically notable for its strategic location and role in Roman-era conflicts.
  • A. Comeng
    Comeng is an Australian engineering and rolling stock manufacturing company best known for producing trains and other rail vehicles used across the country.
  • B. Cortalim
    Cortalim is a village in South Goa, India, known for its scenic riverside location, historic churches, and role as a transport hub near the Zuari River.
  • C. Sogeti
    Sogeti is a professional services and technology consulting company specializing in IT and engineering solutions, operating as a subsidiary of Capgemini.
  • D. Compans
    Compans is a small French commune located in the Seine-et-Marne department in the Île-de-France region, northeast of Paris.
  • E. Kompa
    Kompa is a popular Haitian dance music genre known for its smooth, guitar-driven rhythms and strong influence on Caribbean and diasporic music styles.
  • 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_69d87f2c6778819080fcfae53be8f12a completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32ce19344819083d323077b742bc3 completed April 18, 2026, 7:04 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0045979c588190b6f7b249147f3174 completed May 10, 2026, 8:45 a.m.
NEDg Description generation batch_6a00472cdc2881908211045515cd21ee completed May 10, 2026, 8:51 a.m.
NED2 Entity disambiguation (via description) batch_6a0047b4b6688190afef52b39788ceae completed May 10, 2026, 8:54 a.m.
Created at: April 10, 2026, 5:10 a.m.