Triple

T10335267
Position Surface form Disambiguated ID Type / Status
Subject Battle of Singara E242985 entity
Predicate locatedIn P40 FINISHED
Object Singara
Singara was an ancient fortified city in northern Mesopotamia, strategically important as a Roman-Persian frontier stronghold.
 E857730 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: Singara | Statement: [Battle of Singara, locatedIn, Singara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Singara
Context triple: [Battle of Singara, locatedIn, Singara]
  • A. Songsarek
    Songsarek is the indigenous animistic religion traditionally practiced by the Garo people of the Garo Hills in northeastern India.
  • B. Songo
    Songo is a small town in Mozambique known primarily for its proximity to the Cahora Bassa Dam and its role in supporting the dam’s operations and nearby communities.
  • C. Sawanih
    Sawanih is a notable literary work by the Indian poet Faizi, recognized for its contribution to classical Persian literature in South Asia.
  • D. Shugni
    Shugni is an Eastern Iranian language spoken primarily in the Badakhshan region of Tajikistan and Afghanistan by the Shughni people.
  • E. Songololo
    Songololo is a town in the western Democratic Republic of the Congo, situated near the border with Angola and known as a local transport and trade hub.
  • 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: Singara
Triple: [Battle of Singara, locatedIn, Singara]
Generated description
Singara was an ancient fortified city in northern Mesopotamia, strategically important as a Roman-Persian frontier stronghold.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Singara
Target entity description: Singara was an ancient fortified city in northern Mesopotamia, strategically important as a Roman-Persian frontier stronghold.
  • A. Songsarek
    Songsarek is the indigenous animistic religion traditionally practiced by the Garo people of the Garo Hills in northeastern India.
  • B. Songo
    Songo is a small town in Mozambique known primarily for its proximity to the Cahora Bassa Dam and its role in supporting the dam’s operations and nearby communities.
  • C. Sawanih
    Sawanih is a notable literary work by the Indian poet Faizi, recognized for its contribution to classical Persian literature in South Asia.
  • D. Shugni
    Shugni is an Eastern Iranian language spoken primarily in the Badakhshan region of Tajikistan and Afghanistan by the Shughni people.
  • E. Songololo
    Songololo is a town in the western Democratic Republic of the Congo, situated near the border with Angola and known as a local transport and trade hub.
  • 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_69d381af787481908bc401325c760a88 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4dfc425748190a3d29f81e32e948b completed April 7, 2026, 10:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69d7505b85048190ad69a4fb5c63c677 completed April 9, 2026, 7:08 a.m.
NEDg Description generation batch_69d7618b0f2481908149596dc86d4593 completed April 9, 2026, 8:21 a.m.
NED2 Entity disambiguation (via description) batch_69d77015ae688190870976309e2b912b completed April 9, 2026, 9:23 a.m.
Created at: April 6, 2026, 11:53 a.m.