Triple
T33529445
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Toumba Stadium |
E858732
|
entity |
| Predicate | cityDerbyHost |
P88080
|
FINISHED |
| Object | PAOK FC vs Aris Thessaloniki FC |
—
|
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: PAOK FC vs Aris Thessaloniki FC | Statement: [Toumba Stadium, cityDerbyHost, PAOK FC vs Aris Thessaloniki FC]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cityDerbyHost Context triple: [Toumba Stadium, cityDerbyHost, PAOK FC vs Aris Thessaloniki FC]
-
A.
cityDerbyHosted
chosen
Indicates that a particular city served as the host location for a specified derby event.
-
B.
cityDerby
Indicates a competitive or rivalry relationship between two cities, often in sports or similar local contests.
-
C.
cityDerbyName
Indicates that a city is known by a particular derby (rivalry match) name.
-
D.
homeCityDerby
Indicates that two sports teams are based in the same city and their match-up constitutes a local rivalry or derby.
-
E.
isFromCityWithDerby
Indicates that an entity originates from a city that has a football (or sports) derby with another team from the same city.
- 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_69f34978caf4819083f90eba4944d8e8 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6f8164698819090c1b471f1caa4c6 |
completed | May 3, 2026, 7:24 a.m. |
| PD | Predicate disambiguation | batch_69f6f6619404819084662aef1238261c |
completed | May 3, 2026, 7:16 a.m. |
Created at: May 1, 2026, 1:39 a.m.