Triple
T22187496
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rome Derby |
E548332
|
entity |
| Predicate | isPlayedInCompetition |
P99442
|
FINISHED |
| Object | Italian Serie A season |
—
|
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: Italian Serie A season | Statement: [Rome Derby, isPlayedInCompetition, Italian Serie A season]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPlayedInCompetition Context triple: [Rome Derby, isPlayedInCompetition, Italian Serie A season]
-
A.
competitionPlayed
Indicates that a competitive event or match has taken place between participants.
-
B.
usedInCompetition
Indicates that something is employed or utilized as part of a competition or contest.
-
C.
hasCompetition
Indicates that one entity is in a state of rivalry or contest with another entity, typically competing for the same goal, resource, or advantage.
-
D.
featuredInCompetition
chosen
Indicates that an entity was included or showcased as a participant or entry in a specific competition.
-
E.
isProfessionalCompetition
Indicates that the relationship involves a competition conducted at a professional level, typically among participants who engage in the activity as their occupation or primary paid pursuit.
- 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_69e11e3e0c7c8190b30d278845e2497e |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12aaa32288190830f6dfc626fb26a |
completed | April 28, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69e71b48576c8190a8e93738fd9cfda5 |
completed | April 21, 2026, 6:38 a.m. |
Created at: April 16, 2026, 8:35 p.m.