Triple
T11753679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Temple (Der Tempel) |
E279469
|
entity |
| Predicate | appliedToStadiumType |
P101180
|
FINISHED |
| Object | football 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: football stadium | Statement: [Temple (Der Tempel), appliedToStadiumType, football stadium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliedToStadiumType Context triple: [Temple (Der Tempel), appliedToStadiumType, football stadium]
-
A.
appliesToStadiumName
Indicates that something is relevant or specifically associated with the name of a stadium.
-
B.
containsStadium
Indicates that a location or area includes a stadium within its boundaries or premises.
-
C.
hasSportsVenueType
Indicates that a sports venue is classified as being of a specific type or category (e.g., stadium, arena, court).
-
D.
hasStadiumUse
Indicates that one entity (typically a team, organization, or event) uses or is authorized to use a particular stadium for its activities or purposes.
-
E.
hostStadiumType
Indicates the type or category of stadium that serves as the host venue for an event or activity.
- 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_69d6ab01038c819080714901502c84fc |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a50b8a14819092a7397d73f0a8e3 |
completed | April 10, 2026, 7:21 a.m. |
| PD | Predicate disambiguation | batch_69d88a813cc48190a3dfdc60e8af80ae |
completed | April 10, 2026, 5:28 a.m. |
| PDg | Predicate description generation | batch_69d890467a2481909ce6c669e739c8de |
completed | April 10, 2026, 5:53 a.m. |
Created at: April 8, 2026, 9:41 p.m.