Triple
T29335568
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Naam Tamilar Katchi |
E743896
|
entity |
| Predicate | stanceOnSriLankanTamils |
P168142
|
FINISHED |
| Object | justice for war crimes |
—
|
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: justice for war crimes | Statement: [Naam Tamilar Katchi, stanceOnSriLankanTamils, justice for war crimes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stanceOnSriLankanTamils Context triple: [Naam Tamilar Katchi, stanceOnSriLankanTamils, justice for war crimes]
-
A.
stanceOnCommonwealth
Indicates a subject’s position, attitude, or policy toward the Commonwealth as a political or organizational entity.
-
B.
stanceOnMedia
Indicates a subject’s expressed attitude, opinion, or position toward a particular media outlet, medium, or piece of media.
-
C.
stanceOnAuthority
Indicates an entity’s attitude, position, or level of support or opposition toward authority or authoritative control.
-
D.
stanceOnArmedStruggle
Indicates a subject’s position or attitude toward the use of armed struggle as a method of pursuing goals or resolving conflicts.
-
E.
stanceOnRace
Indicates a subject’s expressed position, attitude, or viewpoint regarding race or racial issues.
- 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_69f09126cfcc8190899b16fbf3c2bf7b |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f673633d288190b52ceb9f8a057c44 |
completed | May 2, 2026, 9:57 p.m. |
| PD | Predicate disambiguation | batch_69f66ec5bf508190ad088b89455252bd |
completed | May 2, 2026, 9:38 p.m. |
| PDg | Predicate description generation | batch_69f67256d064819094be04fc1bbbc635 |
completed | May 2, 2026, 9:53 p.m. |
Created at: April 28, 2026, 1:30 p.m.