Triple
T11278611
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hertha BSC |
E267002
|
entity |
| Predicate | wonGermanChampionshipInSeason |
P10823
|
FINISHED |
| Object | 1930 |
—
|
LITERAL 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: 1930 | Statement: [Hertha BSC, wonGermanChampionshipInSeason, 1930]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wonGermanChampionshipInSeason Context triple: [Hertha BSC, wonGermanChampionshipInSeason, 1930]
-
A.
wonChampionshipInSeason
chosen
Indicates that an entity secured a championship title during a specified season.
-
B.
numberOfGermanChampionships
Indicates the count of German championship titles associated with a given entity.
-
C.
wonBundesligaWith
Indicates that one entity achieved victory in the Bundesliga while being associated with (e.g., playing for or coaching) the other entity.
-
D.
leagueChampionshipSeason
Indicates the relationship between a sports league and a specific season in which its championship competition takes place.
-
E.
wonStanleyCupInSeason
Indicates that a team secured the Stanley Cup championship title in a specified hockey season.
- F. None of above.
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_69d6aac8c2f48190ad0596f1f89f0470 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e967ebb4819080b09ed3cec44e77 |
completed | April 9, 2026, 6:01 p.m. |
| PD | Predicate disambiguation | batch_69d787a240588190aa097298f951c915 |
completed | April 9, 2026, 11:04 a.m. |
Created at: April 8, 2026, 9:31 p.m.