Triple
T22743256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IOC Session in Lausanne |
E562473
|
entity |
| Predicate | competingCandidateCity |
P94944
|
FINISHED |
| Object | Paris |
—
|
NE NERFINISHED |
How this triple was built (3 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: Paris | Statement: [IOC Session in Lausanne, competingCandidateCity, Paris]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paris Context triple: [IOC Session in Lausanne, competingCandidateCity, Paris]
-
A.
Paris
chosen
Paris is the capital and largest city of France, renowned for its historic architecture, art, fashion, and cultural influence worldwide.
-
B.
Paris
Paris is a prince of Troy in Greek mythology, best known for judging the beauty contest of the goddesses and for abducting Helen, which sparked the Trojan War.
-
C.
Paris
Paris is an American hip hop artist and producer known for his politically charged, socially conscious lyrics and militant themes.
-
D.
Paris
Paris is a major Chilean department store and retail chain offering a wide range of apparel, home goods, and consumer products.
-
E.
Paris
Paris is a budget-oriented AMD Sempron processor core designed for entry-level desktop computing.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: competingCandidateCity Context triple: [IOC Session in Lausanne, competingCandidateCity, Paris]
-
A.
electoralCompetitionWith
Indicates a relationship where two or more political actors or parties actively compete against each other in an electoral process for votes or office.
-
B.
opponentCandidate
Indicates that one entity is a rival or competing candidate against another in the same contest or election.
-
C.
electionOpponent
Indicates that two individuals are rivals competing against each other in the same election.
-
D.
campaignOpponent
Indicates that one entity is an opponent or rival of another in a political or similar competitive campaign.
-
E.
capitalCandidate
chosen
Indicates that an entity is being considered or proposed as the capital of a given region or political unit.
- 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_69e245513a5c81908d5cb471b4fc429d |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17974c3208190ae1d6b05639cc942 |
completed | April 29, 2026, 3:22 a.m. |
| PD | Predicate disambiguation | batch_69eed2b88d88819096015deb6a648801 |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:23 p.m.