Triple
T26164560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sir Creek dispute |
E654210
|
entity |
| Predicate | hasSecurityIncidents |
P30019
|
FINISHED |
| Object | arrests of fishermen |
—
|
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: arrests of fishermen | Statement: [Sir Creek dispute, hasSecurityIncidents, arrests of fishermen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSecurityIncidents Context triple: [Sir Creek dispute, hasSecurityIncidents, arrests of fishermen]
-
A.
securityIncidents
Indicates that one or more security-related breaches, threats, or violations have occurred involving the referenced entities.
-
B.
hasSecurityEvent
chosen
Indicates that a security-related incident or event is associated with, or has occurred for, a given entity.
-
C.
hasNotableIncident
Indicates that an entity is associated with a significant or noteworthy event, occurrence, or incident.
-
D.
hasBreaches
Indicates that one entity experiences, contains, or is affected by one or more security, structural, or policy breaches associated with another entity.
-
E.
hasSecurityInfrastructure
Indicates that one entity possesses, implements, or is equipped with security-related systems, measures, or infrastructure in relation to another entity or context.
- 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_69ee5b44391c81908bdbd8813ba9aa99 |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f73ae120bc8190bff94d38d7a7a00d |
completed | May 3, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69f73a38d0848190aa5139144b8561c6 |
completed | May 3, 2026, 12:06 p.m. |
Created at: April 26, 2026, 8:32 p.m.