Triple

T18460861
Position Surface form Disambiguated ID Type / Status
Subject Unterland E451026 entity
Predicate ISO3166-2Code P208 FINISHED
Object LI-02
LI-02 is the ISO 3166-2 subdivision code assigned to the Unterland electoral district of Liechtenstein.
E1325394 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: LI-02 | Statement: [Unterland, ISO3166-2Code, LI-02]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: LI-02
Context triple: [Unterland, ISO3166-2Code, LI-02]
  • A. Li-2T
    Li-2T is a transport and paratroop variant of the Soviet Lisunov Li-2 aircraft, adapted for military cargo and troop-carrying roles.
  • B. AL-02
    AL-02 is the shorthand designation for Alabama's 2nd congressional district, a U.S. House of Representatives district covering parts of southeastern Alabama.
  • C. WI-02
    WI-02 is the commonly used shorthand for Wisconsin's 2nd congressional district, a U.S. House of Representatives district centered around the Madison area.
  • D. OLI-2
    OLI-2 is the Operational Land Imager sensor aboard the Landsat 9 satellite, designed to capture multispectral Earth observation imagery for environmental monitoring and land-use analysis.
  • E. FI-02
    FI-02 is the ISO 3166-2 code that designates the region of Southwest Finland within the national subdivision system of Finland.
  • 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: LI-02
Triple: [Unterland, ISO3166-2Code, LI-02]
Generated description
LI-02 is the ISO 3166-2 subdivision code assigned to the Unterland electoral district of Liechtenstein.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: LI-02
Target entity description: LI-02 is the ISO 3166-2 subdivision code assigned to the Unterland electoral district of Liechtenstein.
  • A. Li-2T
    Li-2T is a transport and paratroop variant of the Soviet Lisunov Li-2 aircraft, adapted for military cargo and troop-carrying roles.
  • B. AL-02
    AL-02 is the shorthand designation for Alabama's 2nd congressional district, a U.S. House of Representatives district covering parts of southeastern Alabama.
  • C. WI-02
    WI-02 is the commonly used shorthand for Wisconsin's 2nd congressional district, a U.S. House of Representatives district centered around the Madison area.
  • D. OLI-2
    OLI-2 is the Operational Land Imager sensor aboard the Landsat 9 satellite, designed to capture multispectral Earth observation imagery for environmental monitoring and land-use analysis.
  • E. FI-02
    FI-02 is the ISO 3166-2 code that designates the region of Southwest Finland within the national subdivision system of Finland.
  • 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_69d8d38345688190b565eac2e4cd7935 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e52a7e65bc8190a824bce5b322c3de completed April 19, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_6a040febab8c819086707e68f2259fe9 completed May 13, 2026, 5:45 a.m.
NEDg Description generation batch_6a0410f9ed708190bd13037037487287 completed May 13, 2026, 5:49 a.m.
NED2 Entity disambiguation (via description) batch_6a0417b159b481908f963cf8b251d898 completed May 13, 2026, 6:18 a.m.
Created at: April 10, 2026, 11:33 a.m.