Triple
T942471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chamber of Summary Procedure of the International Court of Justice |
E20336
|
entity |
| Predicate | canHear |
P22020
|
FINISHED |
| Object | disputes between States |
—
|
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: disputes between States | Statement: [Chamber of Summary Procedure of the International Court of Justice, canHear, disputes between States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canHear Context triple: [Chamber of Summary Procedure of the International Court of Justice, canHear, disputes between States]
-
A.
mayHear
Indicates that one entity is permitted or able to hear sounds, speech, or audio produced by another entity.
-
B.
hears
Indicates that one entity perceives or detects sounds produced by another entity or source.
-
C.
hasSpeech
Indicates that an entity produces, delivers, or is associated with a spoken utterance or verbal expression.
-
D.
canBe
Indicates that one entity has the potential, permission, or capability to become, perform as, or be classified as another entity.
-
E.
hadListeningEventAt
Indicates that a listening event involving an entity occurred at a specific time or place.
- 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_69a493b0270c81909e6c9ce310f6aa55 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b3a1a4888190997adf56eb761431 |
completed | March 1, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69a4b29dc8dc8190b9d33f70f8563d61 |
completed | March 1, 2026, 9:41 p.m. |
| PDg | Predicate description generation | batch_69a4b344f6f48190ba03ce593c94176b |
completed | March 1, 2026, 9:44 p.m. |
Created at: March 1, 2026, 7:40 p.m.