Triple
T19404879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alameda campus |
E485426
|
entity |
| Predicate | city |
P40
|
FINISHED |
| Object | Lisbon |
—
|
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: Lisbon | Statement: [Alameda campus, city, Lisbon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lisbon Context triple: [Alameda campus, city, Lisbon]
-
A.
Lisbon
chosen
Lisbon is the coastal capital city of Portugal, renowned for its historic architecture, hilly landscape, and role as a major cultural and economic center in Europe.
-
B.
Lisbon
Lisbon is the alias of Raquel Murillo, a former police inspector who becomes one of the central members of the Professor’s gang in the Spanish series "Money Heist" (La Casa de Papel).
-
C.
Lisbon
Lisbon is a small village in Kendall County, Illinois, United States, known for its rural character and tight-knit community.
-
D.
Porto
Porto is Portugal’s second-largest city, renowned for its historic riverside district, rich maritime heritage, and production of port wine.
-
E.
Porto
Porto is a small coastal town in western Corsica, France, known as the main gateway to the scenic Gulf of Porto and its surrounding natural reserves and rock formations.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8d5162481909db12435d9535c1a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6257a361c8190bf019fc350faa225 |
completed | April 20, 2026, 1:09 p.m. |
Created at: April 10, 2026, 1:36 p.m.