Triple
T6232560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nifrel |
E139390
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Expo City |
E264933
|
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: Expo City | Statement: [Nifrel, near, Expo City]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Expo City Context triple: [Nifrel, near, Expo City]
-
A.
Expo City (entertainment and shopping complex)
chosen
Expo City is a large entertainment and shopping complex in Suita, Osaka, featuring a mix of retail stores, restaurants, cinemas, and family-oriented attractions near the former Expo ’70 site.
-
B.
Ciudad Expo
Ciudad Expo is a metro station on the Seville Metro network serving the municipality of Mairena del Aljarafe in the Seville metropolitan area.
-
C.
AsiaWorld-Expo
AsiaWorld-Expo is a major convention and exhibition center in Hong Kong that hosts large-scale trade shows, concerts, and events.
-
D.
The Expo
The Expo is a well-known multipurpose event and exhibition venue in Portland, Oregon, hosting trade shows, conventions, and community events.
-
E.
Expo City Dubai
Expo City Dubai is a sustainable, mixed-use urban district in Dubai that evolved from the Expo 2020 site into a permanent hub for innovation, business, and culture.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c008b0e7ac8190808a59573ee646f3 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c062ee6f088190bf72692eb8ffb761 |
completed | March 22, 2026, 9:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c20defd338819099a23d00107c4edd |
completed | March 24, 2026, 4:07 a.m. |
Created at: March 22, 2026, 4:22 p.m.