Triple
T11120000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Conference of the Parties to the Minamata Convention |
E262989
|
entity |
| Predicate | firstSessionHeldInYear |
P28016
|
FINISHED |
| Object | 2017 |
—
|
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: 2017 | Statement: [Conference of the Parties to the Minamata Convention, firstSessionHeldInYear, 2017]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstSessionHeldInYear Context triple: [Conference of the Parties to the Minamata Convention, firstSessionHeldInYear, 2017]
-
A.
firstSessionHeldIn
chosen
Indicates that the initial or inaugural session of an event, activity, or process took place in a specified location or context.
-
B.
firstMeetingYear
Indicates the calendar year in which two entities first met or had their initial encounter.
-
C.
firstAppointmentsYear
Indicates the calendar year in which the first appointments or initial assignments to a role, position, or service took place.
-
D.
secondSessionStartYear
Indicates the calendar year in which an entity’s second session begins.
-
E.
yearOfMeeting
Indicates the specific calendar year in which the meeting between the referenced entities took place.
- 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_69d6aa9b46cc8190b19f9f0cc45bf322 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d79af7b72c8190a19dbcbb3a69fb5b |
completed | April 9, 2026, 12:26 p.m. |
| PD | Predicate disambiguation | batch_69d7441efe948190ae4ab020121e169d |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:28 p.m.