Triple
T17823863
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Angkor Thom |
E445059
|
entity |
| Predicate | nearbyCity |
P350
|
FINISHED |
| Object | Siem Reap |
—
|
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: Siem Reap | Statement: [Angkor Thom, nearbyCity, Siem Reap]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Siem Reap Context triple: [Angkor Thom, nearbyCity, Siem Reap]
-
A.
Siem Reap Province
chosen
Siem Reap Province is a northwestern region of Cambodia best known as the gateway to the ancient Khmer temple complex of Angkor, including the iconic Angkor Wat.
-
B.
Meiktila
Meiktila is a city in central Myanmar that served as a key strategic location during World War II, particularly in the Burma Campaign.
-
C.
Krong Reap
Krong Reap is the primary demon antagonist in the Khmer epic Reamker, the Cambodian adaptation of the Ramayana.
-
D.
Battambang
Battambang is a major city in northwestern Cambodia known for its well-preserved French colonial architecture, nearby ancient temples, and role as a cultural and agricultural hub.
-
E.
Buyeo
Buyeo was an ancient Korean kingdom that emerged in northern Manchuria and northern Korea, playing a key role in the early formation of Korean states and culture.
- 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_69d8b9f0de78819099395b14db75a8a6 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4891352ac8190ad3d669fea1c9fbb |
completed | April 19, 2026, 7:49 a.m. |
Created at: April 10, 2026, 10:15 a.m.