Triple
T161026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Korean Armistice Agreement |
E3285
|
entity |
| Predicate | lengthOfDMZ |
P266
|
FINISHED |
| Object | approximately 250 kilometers |
—
|
LITERAL 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: approximately 250 kilometers | Statement: [Korean Armistice Agreement, lengthOfDMZ, approximately 250 kilometers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lengthOfDMZ Context triple: [Korean Armistice Agreement, lengthOfDMZ, approximately 250 kilometers]
-
A.
militaryDistrict
Indicates that an entity functions as, or is located within, an administrative military district or region under military jurisdiction.
-
B.
shorelineLength
Indicates the total measured extent of a land area’s boundary where it meets a body of water.
-
C.
length
chosen
Indicates a measurement relationship where a value specifies how long something is from one end to the other.
-
D.
hasMilitaryBase
Indicates that one entity possesses, hosts, or contains a military base associated with or located on another entity.
-
E.
flightDistance
Indicates the measured distance covered by a flight between its origin and destination.
- F. None of above.
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_69a2527757ec819090b8becb2cf1a862 |
completed | Feb. 28, 2026, 2:27 a.m. |
| NER | Named-entity recognition | batch_69a25856d934819095460b2ea566eb6b |
completed | Feb. 28, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69a256623704819089d9eeefe05858ce |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:31 a.m.