Triple
T1177980
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moldova |
E25071
|
entity |
| Predicate | unAdmissionDate |
P10477
|
FINISHED |
| Object | 1992-03-02 |
—
|
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: 1992-03-02 | Statement: [Moldova, unAdmissionDate, 1992-03-02]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: unAdmissionDate Context triple: [Moldova, unAdmissionDate, 1992-03-02]
-
A.
ordinationDate
Indicates the date on which an individual was formally ordained to a religious office or role.
-
B.
UNAdmissionDate
chosen
Indicates the date on which an entity was officially admitted as a member of the United Nations.
-
C.
hasAdmission
Indicates that an entity possesses or is associated with a specific admission event, record, or status (such as being admitted to a place, program, or institution).
-
D.
admissionOrder
Indicates the sequence or priority in which admissions occur or are processed relative to one another.
-
E.
admissionType
Indicates the category or manner in which an entity (such as a person or case) is formally accepted or admitted into a system, institution, or process.
- 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_69a494267b4c819088c97a59182bf56a |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bd53e4b48190abb2167f8074a6bc |
completed | March 1, 2026, 10:27 p.m. |
| PD | Predicate disambiguation | batch_69a4bb5844348190b01ac6506906ba3b |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:45 p.m.