Triple

T9460457
Position Surface form Disambiguated ID Type / Status
Subject Zaranj E228131 entity
Predicate hasRoadConnectionTo P11435 FINISHED
Object Milak
Milak is a border town in India’s Uttar Pradesh state, known as a road-linked crossing point on the route to Afghanistan via Zaranj.
E800906 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: Milak | Statement: [Zaranj, hasRoadConnectionTo, Milak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Milak
Context triple: [Zaranj, hasRoadConnectionTo, Milak]
  • A. Miklas
    Miklas is an Austrian surname most notably borne by Wilhelm Miklas, who served as President of Austria from 1928 to 1938.
  • B. Michal
    Michal is a mentally impaired and childlike character in Martin McDonagh’s dark play "The Pillowman," whose actions and relationship with his brother Katurian are central to the story’s moral and emotional conflict.
  • C. Michal
    Michal is a biblical figure, a daughter of King Saul who became the first wife of King David in the Hebrew Bible.
  • D. Marek
    Marek is a common given name in several Slavic countries, equivalent to the Latin name Marcus.
  • E. Matúš
    Matúš is the Slovak form of the given name Matthew, commonly used in Slovakia and other Slovak-speaking 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: Milak
Triple: [Zaranj, hasRoadConnectionTo, Milak]
Generated description
Milak is a border town in India’s Uttar Pradesh state, known as a road-linked crossing point on the route to Afghanistan via Zaranj.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Milak
Target entity description: Milak is a border town in India’s Uttar Pradesh state, known as a road-linked crossing point on the route to Afghanistan via Zaranj.
  • A. Miklas
    Miklas is an Austrian surname most notably borne by Wilhelm Miklas, who served as President of Austria from 1928 to 1938.
  • B. Michal
    Michal is a biblical figure, a daughter of King Saul who became the first wife of King David in the Hebrew Bible.
  • C. Michal
    Michal is a mentally impaired and childlike character in Martin McDonagh’s dark play "The Pillowman," whose actions and relationship with his brother Katurian are central to the story’s moral and emotional conflict.
  • D. Marek
    Marek is a common given name in several Slavic countries, equivalent to the Latin name Marcus.
  • E. Matúš
    Matúš is the Slovak form of the given name Matthew, commonly used in Slovakia and other Slovak-speaking 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_69ca843b123881909b0e60028475d12d completed March 30, 2026, 2:10 p.m.
NER Named-entity recognition batch_69cd7fcaf610819092bcd3b871665aa5 completed April 1, 2026, 8:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1229ec9448190bac9b7a38e030833 completed April 4, 2026, 2:39 p.m.
NEDg Description generation batch_69d1245db2e48190a56a797a681316d9 completed April 4, 2026, 2:46 p.m.
NED2 Entity disambiguation (via description) batch_69d124c2a48c819098a24dd2aac734e1 completed April 4, 2026, 2:48 p.m.
Created at: March 30, 2026, 7:52 p.m.