Triple

T6894297
Position Surface form Disambiguated ID Type / Status
Subject Citilink E159131 entity
Predicate callsign P1565 FINISHED
Object SUPERGREEN
SUPERGREEN is the airline callsign used by Citilink, a low-cost carrier based in Indonesia.
E626712 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: SUPERGREEN | Statement: [Citilink, callsign, SUPERGREEN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SUPERGREEN
Context triple: [Citilink, callsign, SUPERGREEN]
  • A. Laird Superfood
    Laird Superfood is a plant-based food and beverage company co-founded by surfer Laird Hamilton, known for its functional creamers, coffees, and performance-focused nutrition products.
  • B. Garden of Life
    Garden of Life is a popular health and wellness brand known for its organic, whole-food-based vitamins, supplements, and protein powders.
  • C. Orgain
    Orgain is a nutrition brand known for its organic protein powders, shakes, and bars focused on clean-label, health-oriented ingredients.
  • D. Organix
    Organix is the first studio album by hip hop band The Roots, showcasing their early jazz-influenced, live-instrument approach to rap music.
  • E. Super Leaf
    Super Leaf is a power-up item in the Super Mario series that transforms Mario into Raccoon Mario, granting him a tail attack and limited flight abilities.
  • 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: SUPERGREEN
Triple: [Citilink, callsign, SUPERGREEN]
Generated description
SUPERGREEN is the airline callsign used by Citilink, a low-cost carrier based in Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: SUPERGREEN
Target entity description: SUPERGREEN is the airline callsign used by Citilink, a low-cost carrier based in Indonesia.
  • A. Laird Superfood
    Laird Superfood is a plant-based food and beverage company co-founded by surfer Laird Hamilton, known for its functional creamers, coffees, and performance-focused nutrition products.
  • B. Garden of Life
    Garden of Life is a popular health and wellness brand known for its organic, whole-food-based vitamins, supplements, and protein powders.
  • C. Orgain
    Orgain is a nutrition brand known for its organic protein powders, shakes, and bars focused on clean-label, health-oriented ingredients.
  • D. Organix
    Organix is the first studio album by hip hop band The Roots, showcasing their early jazz-influenced, live-instrument approach to rap music.
  • E. Super Leaf
    Super Leaf is a power-up item in the Super Mario series that transforms Mario into Raccoon Mario, granting him a tail attack and limited flight abilities.
  • 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_69c6883568c8819081db6407e892cccc completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d931da24819096b9b205f2c0ebb0 completed March 27, 2026, 7:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69c748db2bd48190bb26f60c58ec8229 completed March 28, 2026, 3:19 a.m.
NEDg Description generation batch_69c749901de081908e5c3ccd324e8191 completed March 28, 2026, 3:22 a.m.
NED2 Entity disambiguation (via description) batch_69c74a0bcddc819084b22925cf57a205 completed March 28, 2026, 3:24 a.m.
Created at: March 27, 2026, 2:24 p.m.