Triple
T30809975
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zerkalnyi Strumin |
E784616
|
entity |
| Predicate | isWellKnownAs |
P144403
|
FINISHED |
| Object | architectural landmark in Kharkiv |
—
|
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: architectural landmark in Kharkiv | Statement: [Zerkalnyi Strumin, isWellKnownAs, architectural landmark in Kharkiv]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isWellKnownAs Context triple: [Zerkalnyi Strumin, isWellKnownAs, architectural landmark in Kharkiv]
-
A.
isWidelyKnownAs
chosen
Indicates that an entity is commonly referred to or recognized by a particular name or label by a broad audience.
-
B.
knowsAs
Indicates that one entity recognizes or refers to another entity by a particular name, alias, or identifier.
-
C.
knownAsBy
Indicates that one entity is referred to or recognized by another entity using a particular name or designation.
-
D.
knewAs
Indicates that one entity was acquainted with or recognized another entity under a particular identity, name, or role.
-
E.
recognizedAs
Indicates that one entity is acknowledged or accepted as having the identity, role, status, or classification of another 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_69f224b4eda48190bd212ce4f3901e56 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69063edbc81909e7735954aabee0b |
completed | May 3, 2026, 12:01 a.m. |
| PD | Predicate disambiguation | batch_69f68b7d2794819092fef8a63f4f3de8 |
completed | May 2, 2026, 11:40 p.m. |
Created at: April 29, 2026, 8:43 p.m.