Triple
T29941105
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HC Sparta Praha vs HC Slavia Praha |
E760499
|
entity |
| Predicate | relatedDerbyName |
P113569
|
FINISHED |
| Object | Pražské hokejové derby |
E1047278
|
NE 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: Pražské hokejové derby | Statement: [HC Sparta Praha vs HC Slavia Praha, relatedDerbyName, Pražské hokejové derby]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedDerbyName Context triple: [HC Sparta Praha vs HC Slavia Praha, relatedDerbyName, Pražské hokejové derby]
-
A.
relatedDerby
Indicates that two entities are connected through participation in, association with, or relevance to the same derby event or competition.
-
B.
hasDerbyName
Indicates that an entity is known by or uses a specific derby name, typically as an alternate or performance-related identity.
-
C.
playsInDerbyWith
Indicates that two entities participate together as opponents or competitors in the same derby event or match.
-
D.
isDerby
chosen
Indicates that a competition or match is a derby, typically involving teams or participants from the same locality or with a strong rivalry.
-
E.
homeDerbyName
Indicates the name of the derby event or match that is played at the entity’s home venue.
- F. None of above.
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_69f22463f3648190a603c3ff305c660b |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_6a01ccd995e48190b6675e463bd0a567 |
completed | May 11, 2026, 12:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a27142a09488190bbc0c58c6545a35b |
completed | June 8, 2026, 7:12 p.m. |
| PD | Predicate disambiguation | batch_6a01cc33177c8190bc0703276618b3ec |
completed | May 11, 2026, 12:31 p.m. |
Created at: April 29, 2026, 6:22 p.m.