Triple
T10538586
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orekhovo |
E248635
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object | G. Mun |
E854167
|
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: G. Mun | Statement: [Orekhovo, architect, G. Mun]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: G. Mun Context triple: [Orekhovo, architect, G. Mun]
-
A.
G. Mun
chosen
G. Mun is an architect known for designing the Polyanka project.
-
B.
Gongman
Gongman is the iconic figure who strikes a large gong in the opening logo sequence of the Rank Organisation’s films.
-
C.
J. Mogul
J. Mogul is a computer scientist and networking researcher known for contributions to Internet protocols and standards, including co-authoring early RFCs.
-
D.
Jungmann
Jungmann is the nickname of the Bücker Bü 131, a German 1930s biplane widely used as a primary trainer aircraft before and during World War II.
-
E.
Mugunghwa-ho
Mugunghwa-ho is a class of South Korean intercity passenger trains operated by Korail, known for providing affordable, slower-speed service connecting major cities and regional areas.
- 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_69d381c5c7448190bec34bee7ec72bac |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d50a5730d88190b266a940faf53f65 |
completed | April 7, 2026, 1:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d90e5b827881909e87651a88976f18 |
completed | April 10, 2026, 2:51 p.m. |
Created at: April 6, 2026, 12:31 p.m.