Triple

T17627667
Position Surface form Disambiguated ID Type / Status
Subject FSV Frankfurt E429890 entity
Predicate formerLeague P5927 FINISHED
Object 3. Liga NE NERFINISHED

How this triple was built (2 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: 3. Liga | Statement: [FSV Frankfurt, formerLeague, 3. Liga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 3. Liga
Context triple: [FSV Frankfurt, formerLeague, 3. Liga]
  • A. 3. Liga chosen
    3. Liga is the third tier of professional football in Germany, sitting below the Bundesliga and 2. Bundesliga in the national league system.
  • B. 2. Liga
    2. Liga is the common shorthand name for Germany’s second-tier professional football league, officially known as the 2. Bundesliga.
  • C. III liga
    III liga is the fourth tier of the Polish football league system, featuring semi-professional and amateur clubs competing in regional groups.
  • D. Liga III
    Liga III is the third tier of the Romanian football league system, featuring semi-professional and amateur clubs competing in regionalized divisions.
  • E. II liga
    II liga is the third tier of the Polish football league system, featuring professional and semi-professional clubs competing below the I liga and Ekstraklasa.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d889e37f308190a6aa0a69daff86c7 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46dbe3a308190a818d04f1a9b15f7 completed April 19, 2026, 5:53 a.m.
Created at: April 10, 2026, 5:52 a.m.