Triple
T622444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Article V (Genocide Convention) |
E14541
|
entity |
| Predicate | inForceSince |
P17807
|
FINISHED |
| Object | 1951-01-12 |
—
|
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: 1951-01-12 | Statement: [Article V (Genocide Convention), inForceSince, 1951-01-12]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inForceSince Context triple: [Article V (Genocide Convention), inForceSince, 1951-01-12]
-
A.
inUseSince
Indicates that an entity has been actively in use starting from a specified point in time.
-
B.
inForceUntil
Indicates that a condition, rule, or agreement remains valid and operative up to a specified time or event.
-
C.
usedSince
Indicates that an entity has been in use starting from a specified point in time and continuing thereafter.
-
D.
inPowerSince
Indicates the point in time from which an entity has continuously held a position of authority or power.
-
E.
knownSince
Indicates the point in time from which one entity has been aware of, acquainted with, or in possession of knowledge about another entity.
- 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_69a4934b17c881909ace8270e8ddd202 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49e402d9c8190936896e3ebb6edc5 |
completed | March 1, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69a49d0069d0819087c83b608f6fc053 |
completed | March 1, 2026, 8:09 p.m. |
| PDg | Predicate description generation | batch_69a49e2107548190af0c1d67cfa475d1 |
completed | March 1, 2026, 8:14 p.m. |
Created at: March 1, 2026, 7:35 p.m.