Triple

T14996450
Position Surface form Disambiguated ID Type / Status
Subject Frankfurt Stadion station E373968 entity
Predicate hasStationCode P1289 FINISHED
Object FFST
FFST is the station code for Frankfurt Stadion station, a railway stop serving the area around Deutsche Bank Park in Frankfurt, Germany.
 E1130937 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: FFST | Statement: [Frankfurt Stadion station, hasStationCode, FFST]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FFST
Context triple: [Frankfurt Stadion station, hasStationCode, FFST]
  • A. FFS
    FFS is the commonly used abbreviation for the Swiss Federal Railways, the national railway company of Switzerland.
  • B. FFS
    FFS is the abbreviation for the Football Federation Samoa, the governing body responsible for overseeing football activities in Samoa.
  • C. 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.
  • D. FFS
    FFS is the station code for Frankfurt (Main) Süd, a major railway station in Frankfurt, Germany.
  • E. FFS
    FFS is the state agency responsible for managing and protecting Florida’s forest resources, including wildfire prevention, suppression, and sustainable forestry.
  • 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: FFST
Triple: [Frankfurt Stadion station, hasStationCode, FFST]
Generated description
FFST is the station code for Frankfurt Stadion station, a railway stop serving the area around Deutsche Bank Park in Frankfurt, Germany.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FFST
Target entity description: FFST is the station code for Frankfurt Stadion station, a railway stop serving the area around Deutsche Bank Park in Frankfurt, Germany.
  • A. 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.
  • B. FFS
    FFS is the station code for Frankfurt (Main) Süd, a major railway station in Frankfurt, Germany.
  • C. FFS
    FFS is the commonly used abbreviation for the Swiss Federal Railways, the national railway company of Switzerland.
  • D. FFS
    FFS is the abbreviation for the Football Federation Samoa, the governing body responsible for overseeing football activities in Samoa.
  • E. FFS
    FFS is the state agency responsible for managing and protecting Florida’s forest resources, including wildfire prevention, suppression, and sustainable forestry.
  • 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_69d85ccc84388190aa151e5173370c8d completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded718e4288190b5e144f82299a194 completed April 15, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe969c3ba88190899f06b185e94ccf completed May 9, 2026, 2:06 a.m.
NEDg Description generation batch_69fe972728dc8190a9cf2a3e984b05a7 completed May 9, 2026, 2:08 a.m.
NED2 Entity disambiguation (via description) batch_69fe9790d1d081908fc94829d3104e07 completed May 9, 2026, 2:10 a.m.
Created at: April 10, 2026, 2:53 a.m.