Triple
T10542509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port of Mariupol |
E248730
|
entity |
| Predicate | statusBefore2022 |
P94446
|
FINISHED |
| Object | one of Ukraine’s largest ports on the Sea of Azov |
—
|
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: one of Ukraine’s largest ports on the Sea of Azov | Statement: [Port of Mariupol, statusBefore2022, one of Ukraine’s largest ports on the Sea of Azov]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: statusBefore2022 Context triple: [Port of Mariupol, statusBefore2022, one of Ukraine’s largest ports on the Sea of Azov]
-
A.
statusAfter2019
Indicates the condition or state of an entity specifically in the period following the year 2019.
-
B.
statusAfter2017
Indicates the status or condition an entity has specifically after the year 2017.
-
C.
legalStatusBefore
Indicates the legal condition or classification that applied to an entity prior to a specified event, change, or point in time.
-
D.
statusAfter2020
Indicates the condition or state of an entity as it exists after the year 2020.
-
E.
statusAfter2018
Indicates the condition or state of something specifically during the period after the year 2018.
- 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_69d381c733c08190ab1dd6239f5f34ae |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d5190f46d08190a92b1191881ffb92 |
completed | April 7, 2026, 2:47 p.m. |
| PD | Predicate disambiguation | batch_69d4fb9729288190a0149f127acd7ae3 |
completed | April 7, 2026, 12:41 p.m. |
| PDg | Predicate description generation | batch_69d4fe06d4a48190b1a45dd1d4e16df0 |
completed | April 7, 2026, 12:52 p.m. |
Created at: April 6, 2026, 12:32 p.m.