Triple
T2202501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Astana |
E50521
|
entity |
| Predicate | hostedEvent |
P613
|
FINISHED |
| Object | Expo 2017 |
E102574
|
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 2017 | Statement: [Astana, hostedEvent, Expo 2017]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Expo 2017 Context triple: [Astana, hostedEvent, Expo 2017]
-
A.
Expo 2017
chosen
Expo 2017 was an international specialized exposition held in Astana, Kazakhstan, focused on the theme of future energy and sustainable development.
-
B.
Expo 2025
Expo 2025 is a World Expo scheduled to be held in Osaka, Japan, focusing on innovation and global collaboration around the theme of designing future societies.
-
C.
Expo 2020
Expo 2020 was a World Expo held in Dubai that showcased global innovation, culture, and sustainability through international pavilions and events.
-
D.
Expo 2015
Expo 2015 was a World Expo held in Milan, Italy, focused on the theme of global food, nutrition, and sustainable development.
-
E.
Expo '75
Expo '75 was a world's fair held in Okinawa, Japan, that showcased marine science and technology while promoting the island's post-reversion development and international exchange.
- 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_69a88b044ab48190add007487680f009 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abbfa33f0881908403604eafb73ecf |
completed | March 7, 2026, 6:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae5dbd583c8190bc7355bdf94d6588 |
completed | March 9, 2026, 5:42 a.m. |
Created at: March 4, 2026, 7:46 p.m.