Triple
T36951399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Belgium national ice hockey team |
E914071
|
entity |
| Predicate | homeCityFor1920Olympics |
P186775
|
FINISHED |
| Object | Antwerp |
—
|
NE NERFINISHED |
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: Antwerp | Statement: [Belgium national ice hockey team, homeCityFor1920Olympics, Antwerp]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeCityFor1920Olympics Context triple: [Belgium national ice hockey team, homeCityFor1920Olympics, Antwerp]
-
A.
homeCityOfNOC
Indicates that a given city is the designated home or base city of a particular National Olympic Committee (NOC).
-
B.
hostCityPreviousOlympicsInCity
Indicates that the city served as the host city for a previous edition of the Olympic Games held in that same city.
-
C.
OlympicCity
Indicates that a city has been designated as a host location for the Olympic Games.
-
D.
hostCityLocatedOn
Indicates that the city serving as a host (e.g., of an event) is geographically situated on or along a specified physical feature or area (such as a river, coast, or region).
-
E.
hostCityPreviousWinterGames
Indicates that the subject city served as the host city for the immediately preceding edition of the Winter Games relative to the event in question.
- 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_69f76e8b28848190abd81fe7a7374910 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fa0a7b00948190a257273d9968c5d7 |
completed | May 5, 2026, 3:19 p.m. |
| PD | Predicate disambiguation | batch_69f9fec9c9488190ae2a349651a02782 |
completed | May 5, 2026, 2:29 p.m. |
| PDg | Predicate description generation | batch_69fa0a799b9081909bfa8293a22c4b00 |
completed | May 5, 2026, 3:19 p.m. |
Created at: May 3, 2026, 4:13 p.m.