Triple
T38463339
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shanghai Dragons |
E912503
|
entity |
| Predicate | wonStageTitle |
P29747
|
FINISHED |
| Object | 2020 May Melee tournament |
—
|
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: 2020 May Melee tournament | Statement: [Shanghai Dragons, wonStageTitle, 2020 May Melee tournament]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wonStageTitle Context triple: [Shanghai Dragons, wonStageTitle, 2020 May Melee tournament]
-
A.
wonTitleWith
chosen
Indicates that an entity secured a specific title, award, or championship while being associated with or representing another entity (such as a team, organization, or group).
-
B.
wonTitleFrom
Indicates that one entity obtained a title or championship by defeating or surpassing another specific entity who previously held it.
-
C.
winnerTitle
Indicates the formal title or designation awarded to the entity that wins a particular competition, contest, or event.
-
D.
wonStatisticTitle
Indicates that an entity has received or achieved a specific statistical title or award, typically based on performance metrics.
-
E.
wonWorldTitleIn
Indicates that an entity achieved victory in a world championship title in a specified competition or year.
- 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_69f76e861d8c81908559031dc66e3c15 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcce7afcd08190906cc3801152656a |
completed | May 7, 2026, 5:40 p.m. |
| PD | Predicate disambiguation | batch_69fcccf140ec8190862d53388a5f40d7 |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:31 p.m.