Triple
T26340140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flag of the Turkish Republic of Northern Cyprus |
E662622
|
entity |
| Predicate | topStripePosition |
P133835
|
FINISHED |
| Object | near upper edge |
—
|
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: near upper edge | Statement: [Flag of the Turkish Republic of Northern Cyprus, topStripePosition, near upper edge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: topStripePosition Context triple: [Flag of the Turkish Republic of Northern Cyprus, topStripePosition, near upper edge]
-
A.
topStripeWidth
Indicates the width measurement of the topmost stripe in a striped object or pattern.
-
B.
topStripeColor
Indicates the color that appears on the topmost stripe of an object or pattern.
-
C.
greenStripePosition
Indicates the relative location or alignment of a green stripe with respect to another part or reference on an object.
-
D.
whiteStripePosition
chosen
Indicates the relative location or alignment of a white stripe within or on an object.
-
E.
bottomStripeWidth
Indicates the width measurement of the stripe located at the bottom of an object or surface.
- 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_69ee81304194819092e20e0fae3aee07 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f60fa1a2e48190894526679b07d59d |
completed | May 2, 2026, 2:52 p.m. |
| PD | Predicate disambiguation | batch_69f5f7ff548c8190a23e98c5e66e0bc7 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 10:38 p.m.