Triple
T24515921
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clássico (Porto vs Sporting) |
E606368
|
entity |
| Predicate | typicalKickoffFrequency |
P30335
|
FINISHED |
| Object | at least twice per season in league |
—
|
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: at least twice per season in league | Statement: [Clássico (Porto vs Sporting), typicalKickoffFrequency, at least twice per season in league]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalKickoffFrequency Context triple: [Clássico (Porto vs Sporting), typicalKickoffFrequency, at least twice per season in league]
-
A.
typicalKickoffType
Indicates the usual or most common type or form of kickoff associated with an event, process, or activity.
-
B.
typicalKickoffSlot
Indicates the usual or standard time slot when a kickoff event (such as a game or meeting) is scheduled to begin.
-
C.
typicalUpdateFrequency
Indicates how often an entity is usually updated or refreshed over time.
-
D.
localKickoffTime
Indicates the scheduled start time of an event as expressed in a specific local time zone.
-
E.
gamesFrequency
chosen
Indicates how often the related entities engage in playing games together or participate in game-related activities.
- 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_69e2c4c725148190a4e41577c5cb409c |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2a9d912e88190bc39c05a9d7f407e |
completed | April 30, 2026, 1:01 a.m. |
| PD | Predicate disambiguation | batch_69f2a6a4580481908fddc385f5262f95 |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:24 a.m.