Triple

T7081050
Position Surface form Disambiguated ID Type / Status
Subject Republic of China Army E164954 entity
Predicate shortName P43 FINISHED
Object ROCA
ROCA is the acronym for the Republic of China Army, the land warfare branch of Taiwan’s armed forces.
E641216 NE FINISHED

How this triple was built (4 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: ROCA | Statement: [Republic of China Army, shortName, ROCA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ROCA
Context triple: [Republic of China Army, shortName, ROCA]
  • A. RC-6
    RC-6 is a mid-size fastback sedan produced by the Chinese automaker Baojun, known for its elevated ride height and crossover-inspired styling.
  • B. RC6
    RC6 is a symmetric block cipher designed as a candidate for the Advanced Encryption Standard (AES), known for its simplicity, efficiency, and parameterized structure.
  • C. RSA Fellowship
    The RSA Fellowship is a global community of accomplished individuals from diverse fields who collaborate to address social challenges and promote innovative solutions for the public good.
  • D. RC2
    RC2 is a symmetric-key block cipher designed by cryptographer Ronald L. Rivest and widely used in early Internet security applications.
  • E. RSA Archer
    RSA Archer is an integrated risk management and governance, risk, and compliance (GRC) software platform used by organizations to identify, assess, and manage enterprise risks and regulatory obligations.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: ROCA
Triple: [Republic of China Army, shortName, ROCA]
Generated description
ROCA is the acronym for the Republic of China Army, the land warfare branch of Taiwan’s armed forces.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: ROCA
Target entity description: ROCA is the acronym for the Republic of China Army, the land warfare branch of Taiwan’s armed forces.
  • A. RC-6
    RC-6 is a mid-size fastback sedan produced by the Chinese automaker Baojun, known for its elevated ride height and crossover-inspired styling.
  • B. RC6
    RC6 is a symmetric block cipher designed as a candidate for the Advanced Encryption Standard (AES), known for its simplicity, efficiency, and parameterized structure.
  • C. RSA Fellowship
    The RSA Fellowship is a global community of accomplished individuals from diverse fields who collaborate to address social challenges and promote innovative solutions for the public good.
  • D. RC2
    RC2 is a symmetric-key block cipher designed by cryptographer Ronald L. Rivest and widely used in early Internet security applications.
  • E. RSA Archer
    RSA Archer is an integrated risk management and governance, risk, and compliance (GRC) software platform used by organizations to identify, assess, and manage enterprise risks and regulatory obligations.
  • F. None of above. chosen

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_69c6887cbc6c8190bdfac42d940f4d8a completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e4f1f5748190b214856bcfc70d81 completed March 27, 2026, 8:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69c79477a79c81909b51175a24d17142 completed March 28, 2026, 8:42 a.m.
NEDg Description generation batch_69c798cd9e4c8190a9dc1176d60d2cf6 completed March 28, 2026, 9:01 a.m.
NED2 Entity disambiguation (via description) batch_69c799fae8608190b0cd94d59ab589a4 completed March 28, 2026, 9:06 a.m.
Created at: March 27, 2026, 2:40 p.m.