Triple
T2053481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | International Criminal Tribunal for Rwanda |
E45621
|
entity |
| Predicate | temporalJurisdictionStart |
P288
|
FINISHED |
| Object | 1994-01-01 |
—
|
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: 1994-01-01 | Statement: [International Criminal Tribunal for Rwanda, temporalJurisdictionStart, 1994-01-01]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: temporalJurisdictionStart Context triple: [International Criminal Tribunal for Rwanda, temporalJurisdictionStart, 1994-01-01]
-
A.
startDate
chosen
Indicates the point in time when an event, state, or relationship begins.
-
B.
createdForJurisdiction
Indicates that something was created specifically to apply within, serve, or be used by a particular legal or geographic jurisdiction.
-
C.
startsAt
Indicates that an event, process, or state begins at a specific time, location, or point in a sequence.
-
D.
historicalJurisdiction
Indicates that one entity previously held legal or administrative authority over another entity during a past time period.
-
E.
dateEnacted
Indicates the date on which a law, policy, or formal measure was officially put into effect or became legally operative.
- 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_69a8891a19508190a12ef1e192308dcb |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb99196ec819096f491ac7732156a |
completed | March 7, 2026, 5:37 a.m. |
| PD | Predicate disambiguation | batch_69abb7abba508190b872f345d3ba51bb |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:39 p.m.