Triple
T27350420
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1991–92 NBA season |
E684343
|
entity |
| Predicate | firstOverallDraftTeam |
P199039
|
FINISHED |
| Object | Charlotte Hornets |
—
|
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: Charlotte Hornets | Statement: [1991–92 NBA season, firstOverallDraftTeam, Charlotte Hornets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstOverallDraftTeam Context triple: [1991–92 NBA season, firstOverallDraftTeam, Charlotte Hornets]
-
A.
firstOverallTeam
Indicates that the referenced team finished in first place overall in a competition, league, or ranking.
-
B.
offensiveRookieOfTheYearTeam
Indicates that a player was selected as the Offensive Rookie of the Year while playing for a specific team.
-
C.
NHLdraftTeam
Indicates the professional ice hockey team that selected a player in the NHL Entry Draft.
-
D.
defensiveRookieOfTheYearTeam
Indicates that a player’s team is the one for which they earned the Defensive Rookie of the Year award.
-
E.
teamFoundedByDraft
Indicates that a sports team was originally established or created through a draft process.
- F. None of above. chosen
Provenance (4 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_69ef1480a76481908684256ddd5bfda3 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69ff1c91bbac8190b84012dee1cb3b2c |
completed | May 9, 2026, 11:37 a.m. |
| PD | Predicate disambiguation | batch_69ff1c23ca508190bb5a435d765b7e53 |
completed | May 9, 2026, 11:36 a.m. |
| PDg | Predicate description generation | batch_69ff1c90c0f48190a3ede7b36ec77cfd |
completed | May 9, 2026, 11:37 a.m. |
Created at: April 27, 2026, 11:48 a.m.