Triple

T16058362
Position Surface form Disambiguated ID Type / Status
Subject Firefly E389540 entity
Predicate ICAOcode P419 FINISHED
Object FFM
FFM is the ICAO airline designator assigned to Firefly, a Malaysian regional airline and subsidiary of Malaysia Airlines.
E1191846 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: FFM | Statement: [Firefly, ICAOcode, FFM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: FFM
Context triple: [Firefly, ICAOcode, FFM]
  • A. FFM
    FFM is an abbreviation commonly used for the Montreal World Film Festival, an international film festival held annually in Montreal, Canada.
  • B. FFS
    FFS is the state agency responsible for managing and protecting Florida’s forest resources, including wildfire prevention, suppression, and sustainable forestry.
  • C. FFS
    FFS is the commonly used abbreviation for the Swiss Federal Railways, the national railway company of Switzerland.
  • D. FFS
    FFS is a high-performance file system originally developed for BSD Unix that introduced improved disk layout and efficiency over earlier Unix file systems.
  • E. FFS
    FFS is the station code for Frankfurt (Main) Süd, a major railway station in Frankfurt, Germany.
  • 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: FFM
Triple: [Firefly, ICAOcode, FFM]
Generated description
FFM is the ICAO airline designator assigned to Firefly, a Malaysian regional airline and subsidiary of Malaysia Airlines.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: FFM
Target entity description: FFM is the ICAO airline designator assigned to Firefly, a Malaysian regional airline and subsidiary of Malaysia Airlines.
  • A. FFM
    FFM is an abbreviation commonly used for the Montreal World Film Festival, an international film festival held annually in Montreal, Canada.
  • B. FFS
    FFS is the commonly used abbreviation for the Swiss Federal Railways, the national railway company of Switzerland.
  • C. FFS
    FFS is the state agency responsible for managing and protecting Florida’s forest resources, including wildfire prevention, suppression, and sustainable forestry.
  • D. FFS
    FFS is a high-performance file system originally developed for BSD Unix that introduced improved disk layout and efficiency over earlier Unix file systems.
  • E. FFS
    FFS is the station code for Frankfurt (Main) Süd, a major railway station in Frankfurt, Germany.
  • 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_69d86dae698881908327ef2d67706cb9 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1837634248190a99cc454ad1e99e0 completed April 17, 2026, 12:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbe678fc8190b36737a9cd29691c completed May 10, 2026, 1:14 a.m.
NEDg Description generation batch_69ffdd2e0c38819091a57098985fa19e completed May 10, 2026, 1:19 a.m.
NED2 Entity disambiguation (via description) batch_69ffde20bd488190a06cedf311e37c80 completed May 10, 2026, 1:23 a.m.
Created at: April 10, 2026, 4:57 a.m.