Triple
T16117762
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Expo permanent markers |
E391048
|
entity |
| Predicate | brand |
P1500
|
FINISHED |
| Object | Expo |
E88623
|
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 | Statement: [Expo permanent markers, brand, Expo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Expo Context triple: [Expo permanent markers, brand, Expo]
-
A.
Expo
Expo is an open-source platform and toolchain for building, deploying, and iterating on React Native applications.
-
B.
Expo
chosen
Expo is a popular brand best known for its dry-erase markers and related whiteboard accessories commonly used in schools, offices, and homes.
-
C.
The Expo
The Expo is a well-known multipurpose event and exhibition venue in Portland, Oregon, hosting trade shows, conventions, and community events.
-
D.
Expo 83
Expo 83 was a specialized international exposition held in Plovdiv, Bulgaria in 1983, showcasing technological, industrial, and cultural achievements.
-
E.
Expo 85
Expo 85 was a world's fair held in Tsukuba, Japan, showcasing advances in science and technology during the mid-1980s.
- 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_69d87f1a8dd881909f1de6ef78849874 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e2016c10a081909b2d23ecea153a9c |
completed | April 17, 2026, 9:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fff2a44cb48190abe3b1ea27349734 |
completed | May 10, 2026, 2:51 a.m. |
Created at: April 10, 2026, 5 a.m.