Triple
T26319967
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National road N20 |
E662078
|
entity |
| Predicate | partlyReclassifiedAs |
P22031
|
FINISHED |
| Object | D720 |
—
|
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: D720 | Statement: [National road N20, partlyReclassifiedAs, D720]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partlyReclassifiedAs Context triple: [National road N20, partlyReclassifiedAs, D720]
-
A.
reclassifiedAs
chosen
Indicates that an entity’s classification or category has been changed from a previous one to a new one.
-
B.
reclassifiedBy
Indicates that an entity’s classification or category has been changed by a specific agent or authority.
-
C.
isSometimesClassifiedAs
Indicates that an entity is occasionally, but not consistently or universally, categorized under a particular type or class.
-
D.
isClassifiedUnder
Indicates that one entity is categorized or grouped within a broader class, type, or category represented by another entity.
-
E.
partlyReclaimedAs
Indicates that one entity has been partially converted, restored, or taken back into the state, use, or condition represented by the other entity.
- 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_69ee812e73048190aae587f1d51e5a06 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f612607c388190ab61d1ac7d18e08d |
completed | May 2, 2026, 3:04 p.m. |
| PD | Predicate disambiguation | batch_69f611a9272881909093360472be832c |
completed | May 2, 2026, 3 p.m. |
Created at: April 26, 2026, 10:27 p.m.