Triple

T12981955
Position Surface form Disambiguated ID Type / Status
Subject Matara District E321672 entity
Predicate hasTown P847 FINISHED
Object Hakmana
Hakmana is a town in Sri Lanka’s Southern Province, known as a local commercial and administrative center within the Matara District.
 E1013904 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: Hakmana | Statement: [Matara District, hasTown, Hakmana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hakmana
Context triple: [Matara District, hasTown, Hakmana]
  • A. Hamutal
    Hamutal was a queen of Judah, known as the mother of the last king of Judah, Zedekiah, during the final years before the Babylonian exile.
  • B. Hekinan
    Hekinan is a coastal industrial city in central Japan known for its manufacturing sector and location along Mikawa Bay in Aichi Prefecture.
  • C. Kashta
    Kashta was a Kushite king of Nubia in the 8th century BCE who began the expansion into Egypt that his successors, including Shabaka, would complete.
  • D. Hudur
    Hudur is a key urban center in southwestern Somalia that serves as an administrative and commercial hub for the surrounding region.
  • E. Huwawa
    Huwawa is a monstrous guardian of the Cedar Forest in ancient Mesopotamian mythology, best known from the Epic of Gilgamesh.
  • 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: Hakmana
Triple: [Matara District, hasTown, Hakmana]
Generated description
Hakmana is a town in Sri Lanka’s Southern Province, known as a local commercial and administrative center within the Matara District.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hakmana
Target entity description: Hakmana is a town in Sri Lanka’s Southern Province, known as a local commercial and administrative center within the Matara District.
  • A. Hamutal
    Hamutal was a queen of Judah, known as the mother of the last king of Judah, Zedekiah, during the final years before the Babylonian exile.
  • B. Hekinan
    Hekinan is a coastal industrial city in central Japan known for its manufacturing sector and location along Mikawa Bay in Aichi Prefecture.
  • C. Kashta
    Kashta was a Kushite king of Nubia in the 8th century BCE who began the expansion into Egypt that his successors, including Shabaka, would complete.
  • D. Hudur
    Hudur is a key urban center in southwestern Somalia that serves as an administrative and commercial hub for the surrounding region.
  • E. Huwawa
    Huwawa is a monstrous guardian of the Cedar Forest in ancient Mesopotamian mythology, best known from the Epic of Gilgamesh.
  • 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_69d8076479b8819090afce3591939cdf completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97e5ca33481909a6cb06c636889f9 completed April 10, 2026, 10:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8f200c88190a2aab15373cbedf5 completed May 3, 2026, 2:54 a.m.
NEDg Description generation batch_69f6ba0904e8819098bae29961bf0046 completed May 3, 2026, 2:59 a.m.
NED2 Entity disambiguation (via description) batch_69f6bb7a0ae08190813411fa677430aa completed May 3, 2026, 3:05 a.m.
Created at: April 9, 2026, 8:39 p.m.