Triple
T604627
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dallas Mavericks |
E11567
|
entity |
| Predicate | wonDivisionTitles |
P10278
|
FINISHED |
| Object | 1987 |
—
|
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: 1987 | Statement: [Dallas Mavericks, wonDivisionTitles, 1987]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wonDivisionTitles Context triple: [Dallas Mavericks, wonDivisionTitles, 1987]
-
A.
wonDivisionTitle
chosen
Indicates that an entity secured first place in its competitive division, earning the division championship title.
-
B.
wonLeagueTitle
Indicates that a team or individual finished a competition as champions, securing the league title for that season or tournament.
-
C.
team1ConferenceTitles
Indicates the number of conference championship titles won by the first team in a given context or comparison.
-
D.
worldSeriesTitles
Indicates the number of World Series championship titles an entity (typically a baseball team) has won.
-
E.
hasChampionships
Indicates that one entity possesses or has won one or more championships associated with another entity.
- 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_69a4932779b881908688590d59c71900 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49e574444819087999404f3e3ffd9 |
completed | March 1, 2026, 8:15 p.m. |
| PD | Predicate disambiguation | batch_69a49cf701e08190966d06b9ff4b582b |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:35 p.m.