Triple

T1458313
Position Surface form Disambiguated ID Type / Status
Subject China Airlines E31449 entity
Predicate ICAOcode P419 FINISHED
Object CAL
CAL is the ICAO airline designator used to identify China Airlines in international aviation operations.
 E168116 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: CAL | Statement: [China Airlines, ICAOcode, CAL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CAL
Context triple: [China Airlines, ICAOcode, CAL]
  • A. CA
    CA is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Canada in international standards and systems.
  • B. CO
    CO is the Italian vehicle registration code for the Province of Como in the Lombardy region.
  • C. CO
    CO is the two-letter ISO 3166-1 alpha-2 country code assigned to Colombia for international identification and standardization purposes.
  • D. SA
    The SA (Sturmabteilung) was the Nazi Party’s paramilitary organization known for its role in Adolf Hitler’s rise to power through intimidation, street violence, and mass rallies in early 20th-century Germany.
  • E. SA
    SA is the two-letter ISO 3166-1 alpha-2 country code representing the Kingdom of Saudi Arabia.
  • 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: CAL
Triple: [China Airlines, ICAOcode, CAL]
Generated description
CAL is the ICAO airline designator used to identify China Airlines in international aviation operations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CAL
Target entity description: CAL is the ICAO airline designator used to identify China Airlines in international aviation operations.
  • A. CA
    CA is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Canada in international standards and systems.
  • B. CO
    CO is the two-letter ISO 3166-1 alpha-2 country code assigned to Colombia for international identification and standardization purposes.
  • C. CO
    CO is the Italian vehicle registration code for the Province of Como in the Lombardy region.
  • D. SA
    The SA (Sturmabteilung) was the Nazi Party’s paramilitary organization known for its role in Adolf Hitler’s rise to power through intimidation, street violence, and mass rallies in early 20th-century Germany.
  • E. SA
    SA is a key 3GPP technical specification group responsible for defining the overall system architecture and service capabilities of mobile telecommunications networks.
  • 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_69a49917dfc081909acdbdf5d684f1ef completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c59a462881908e84b27846a6bc04 completed March 1, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad0e7643e081909a088035faf2022d completed March 8, 2026, 5:51 a.m.
NEDg Description generation batch_69ad121fee9c81909efddee10191b791 completed March 8, 2026, 6:07 a.m.
NED2 Entity disambiguation (via description) batch_69ad127f25548190bdbcf99132237ad4 completed March 8, 2026, 6:09 a.m.
Created at: March 1, 2026, 8 p.m.