Triple
T4339451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | pre-1969 Irish Republican Army |
E97542
|
entity |
| Predicate | consideredItself |
P18566
|
FINISHED |
| Object | legitimate army of the Irish Republic |
—
|
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: legitimate army of the Irish Republic | Statement: [pre-1969 Irish Republican Army, consideredItself, legitimate army of the Irish Republic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: consideredItself Context triple: [pre-1969 Irish Republican Army, consideredItself, legitimate army of the Irish Republic]
-
A.
considersItself
chosen
Indicates that an entity regards or perceives itself in a particular way, role, or state.
-
B.
considered
Indicates that one entity regards, judges, or thinks about another entity in a particular way or context.
-
C.
couldConsider
Indicates that one entity has the potential or option to take another entity into account when making a decision, judgment, or evaluation.
-
D.
considersKilling
Indicates that one entity is contemplating or evaluating the possibility of killing another entity.
-
E.
consideredPartOf
Indicates that one entity is regarded or treated as a component, segment, or subset of another entity within a larger whole.
- 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_69b3454662a481908fbcd0bbfaa3a0a4 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3516f92588190bdf004d8020c1203 |
completed | March 12, 2026, 11:51 p.m. |
| PD | Predicate disambiguation | batch_69b34f4fe1c481908d6d66e15697c04b |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:14 p.m.