Triple
T34908467
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Africa/Kinshasa |
E1006795
|
entity |
| Predicate | hasSameOffsetAllYear |
P136721
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Africa/Kinshasa, hasSameOffsetAllYear, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSameOffsetAllYear Context triple: [Africa/Kinshasa, hasSameOffsetAllYear, true]
-
A.
sameUTCOffsetAs
Indicates that two time-related entities share the same offset from Coordinated Universal Time (UTC), regardless of their specific time zones or locations.
-
B.
offsetFromUTCAllYear
chosen
Indicates that the time-related entity maintains a constant, unchanging offset from Coordinated Universal Time (UTC) throughout the entire year, without seasonal adjustments such as daylight saving time.
-
C.
isSimilarOffsetTo
Indicates that one entity has an offset or displacement that closely matches or corresponds to the offset or displacement of another entity.
-
D.
hasTimeOffset
Indicates that one temporal value is shifted or displaced from another by a specified amount of time.
-
E.
isOffsetFrom
Indicates that one entity’s position, value, or occurrence is displaced by a specified amount or direction relative to 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_69f76dc1b4a081909b4c6e4d8ec0aa2d |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f7cec454a88190a9f3bbee2b856636 |
completed | May 3, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69f7c8977c288190997a892ec5f756ed |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4 p.m.