Triple
T15597230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ProA |
E374932
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | ProA |
E374932
|
NE FINISHED |
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: ProA | Statement: [ProA, abbreviation, ProA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ProA Context triple: [ProA, abbreviation, ProA]
-
A.
ProA
chosen
ProA is the second-highest professional basketball league in Germany, sitting just below the Basketball Bundesliga in the national league system.
-
B.
Pro A
Pro A is the top-tier professional basketball league in Latvia, organized under the Latvian National Basketball League (LNB).
-
C.
ProB
ProB is a lower-tier football league in the French league system, positioned below the top professional division.
-
D.
B.League
B.League is Japan’s professional men’s basketball league, featuring top-tier teams from across the country.
-
E.
ABA League
The ABA League is a top-tier regional professional basketball competition featuring leading clubs from the former Yugoslav countries in Southeast Europe.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d85cce25008190b13b52745fbd719b |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e609ab081909feb486a57439960 |
completed | April 16, 2026, 2:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff678821a481908378db1ffc76ba05 |
completed | May 9, 2026, 4:57 p.m. |
Created at: April 10, 2026, 4:12 a.m.