Triple
T37687301
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sculeni border crossing |
E938404
|
entity |
| Predicate | timeZoneSideMoldova |
P189186
|
FINISHED |
| Object | Eastern European Time |
—
|
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: Eastern European Time | Statement: [Sculeni border crossing, timeZoneSideMoldova, Eastern European Time]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeZoneSideMoldova Context triple: [Sculeni border crossing, timeZoneSideMoldova, Eastern European Time]
-
A.
timeZoneSideRomania
Indicates that the referenced entity is located on the same time zone side or offset alignment as Romania.
-
B.
timeZoneOnBelarusianSide
Indicates that the referenced time zone is the one used on the Belarusian side of a border, region, or context involving Belarus.
-
C.
timeZoneSideUkraine
Indicates that one entity is located on the Ukrainian side of a time zone boundary or within the time zone region associated with Ukraine.
-
D.
timeZoneOnRussianSide
Indicates that the referenced time zone is the one used on the Russian side of a border, region, or cross-border context.
-
E.
timeZoneSideMontenegro
Indicates that one entity is located on the Montenegro side of a time zone boundary or division.
- F. None of above. chosen
Provenance (4 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_69f76ed881408190bc62a969530a4a53 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbb9e8108c8190ae1c7940b1677e95 |
completed | May 6, 2026, 10 p.m. |
| PD | Predicate disambiguation | batch_69fbb141605c8190b9c27d70352522db |
completed | May 6, 2026, 9:23 p.m. |
| PDg | Predicate description generation | batch_69fbb9e69b7481909beaf8264d87c5e5 |
completed | May 6, 2026, 10 p.m. |
Created at: May 3, 2026, 4:18 p.m.