Triple
T20628385
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The RCR |
E506880
|
entity |
| Predicate | battleHonour |
P12198
|
FINISHED |
| Object | Kapyong |
—
|
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: Kapyong | Statement: [The RCR, battleHonour, Kapyong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kapyong Context triple: [The RCR, battleHonour, Kapyong]
-
A.
Kapyong
chosen
Kapyong is a Korean War battlefield in South Korea renowned for a pivotal 1951 engagement in which outnumbered UN forces, including Canadian troops, halted a major Chinese offensive.
-
B.
Guanito
Guanito is a rural municipal district within the San Juan de la Maguana municipality in the San Juan Province of the Dominican Republic.
-
C.
Kalaong
Kalaong is a barangay (village-level administrative division) of the municipality of Maitum in the province of Sarangani, Philippines.
-
D.
Kiaracondong
Kiaracondong is a district in Bandung, West Java, Indonesia, known for its busy railway station and dense urban residential areas.
-
E.
Kawkaban
Kawkaban is a historic fortified mountain town in Yemen renowned for its strategic clifftop location and traditional architecture.
- 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_69e0b4bd4a0081908d4e97a590a33fb2 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6abe645888190b639ebedc5b3041a |
completed | April 20, 2026, 10:42 p.m. |
Created at: April 16, 2026, 11:42 a.m.