Triple

T26371747
Position Surface form Disambiguated ID Type / Status
Subject National Security Council (Republic of China) E660790 entity
Predicate alsoKnownAs P39 FINISHED
Object ROC National Security Council
The ROC National Security Council is Taiwan’s top government body responsible for advising the president and coordinating national security and defense policy.
E1721512 NE 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: ROC National Security Council | Statement: [National Security Council (Republic of China), alsoKnownAs, ROC National Security Council]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: ROC National Security Council
Triple: [National Security Council (Republic of China), alsoKnownAs, ROC National Security Council]
Generated description
The ROC National Security Council is Taiwan’s top government body responsible for advising the president and coordinating national security and defense policy.

Provenance (5 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_69ee812a698881908d6a58265995fa39 completed April 26, 2026, 9:18 p.m.
NER Named-entity recognition batch_69f6103043288190b762b7e1eda5a46b completed May 2, 2026, 2:54 p.m.
NED1 Entity disambiguation (via context triple) batch_6a119a7380388190ad5256f2810464bd completed May 23, 2026, 12:15 p.m.
NEDg Description generation batch_6a119b68c76881908cfa0df6ce3df53c completed May 23, 2026, 12:19 p.m.
NED2 Entity disambiguation (via description) batch_6a119c7d5eac8190ae6fbb97bf64b472 completed May 23, 2026, 12:24 p.m.
Created at: April 26, 2026, 10:58 p.m.