Triple
T3106155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prosecutor v. Thomas Lubanga Dyilo |
E64834
|
entity |
| Predicate | reparationsType |
P45969
|
FINISHED |
| Object | collective reparations |
—
|
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: collective reparations | Statement: [Prosecutor v. Thomas Lubanga Dyilo, reparationsType, collective reparations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reparationsType Context triple: [Prosecutor v. Thomas Lubanga Dyilo, reparationsType, collective reparations]
-
A.
redemptionType
Indicates the manner or method by which something (such as a benefit, reward, or obligation) can be redeemed or fulfilled.
-
B.
typeOfAmnesty
Indicates the specific category or kind of amnesty that applies in a given legal or political context.
-
C.
loanType
Indicates the specific category or kind of loan associated with an entity or transaction.
-
D.
reform
Indicates bringing about significant changes to an existing system, practice, or entity in order to improve or correct it.
-
E.
adjustmentType
Indicates the specific kind or category of modification applied to an existing value, state, or configuration within the relationship.
- 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_69ad857eeaf48190b34ebfdaa7a264cf |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada29beff08190b6e1eb6b0608d0eb |
completed | March 8, 2026, 4:23 p.m. |
| PD | Predicate disambiguation | batch_69ad9df25d4c81908ff0f6cff55d0563 |
completed | March 8, 2026, 4:04 p.m. |
| PDg | Predicate description generation | batch_69ada0f6fef48190b13898be383a246b |
completed | March 8, 2026, 4:16 p.m. |
Created at: March 8, 2026, 3:04 p.m.