Triple
T5051217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shenyang Olympic Sports Center Stadium |
E113787
|
entity |
| Predicate | hasSpectatorCapacityClass |
P16993
|
FINISHED |
| Object | large stadium |
—
|
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: large stadium | Statement: [Shenyang Olympic Sports Center Stadium, hasSpectatorCapacityClass, large stadium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpectatorCapacityClass Context triple: [Shenyang Olympic Sports Center Stadium, hasSpectatorCapacityClass, large stadium]
-
A.
hasSpectatorType
Indicates that an event or activity is associated with a particular category or type of spectator.
-
B.
hasSpectatorArea
Indicates that a location or facility includes a designated area intended for spectators to observe an event or activity.
-
C.
hasSpectators
Indicates that an event, activity, or occurrence is being watched or attended by one or more spectators.
-
D.
audienceCapacityType
chosen
Indicates the classification or type of capacity used to describe how many audience members a venue or event space can accommodate.
-
E.
hasStandingCapacity
Indicates that an entity is capable of maintaining or supporting a specified condition, function, or load on an ongoing basis.
- 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_69bd443aa1f88190abb992d138f2cf42 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7426fc8081908a8227f73168c235 |
completed | March 20, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_69bd715479f08190933604aebd34414f |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:37 p.m.