Triple

T34810969
Position Surface form Disambiguated ID Type / Status
Subject assassination of Robert F. Kennedy E1003495 entity
Predicate otherVictim P31963 FINISHED
Object Ira Goldstein
Ira Goldstein was one of the additional individuals wounded during the 1968 assassination of U.S. Senator Robert F. Kennedy in Los Angeles.
E2210046 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: Ira Goldstein | Statement: [assassination of Robert F. Kennedy, otherVictim, Ira Goldstein]
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: Ira Goldstein
Triple: [assassination of Robert F. Kennedy, otherVictim, Ira Goldstein]
Generated description
Ira Goldstein was one of the additional individuals wounded during the 1968 assassination of U.S. Senator Robert F. Kennedy in Los Angeles.

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_69f76db600b88190989abdf08fce3b27 completed May 3, 2026, 3:45 p.m.
NER Named-entity recognition batch_69f78ba3e28081908c236f60c1f6a28d completed May 3, 2026, 5:53 p.m.
NED1 Entity disambiguation (via context triple) batch_6a3e8c1390c4819084f740a29c6a156c completed June 26, 2026, 2:26 p.m.
NEDg Description generation batch_6a3e94bce86c8190b025e79699e31e7e completed June 26, 2026, 3:03 p.m.
NED2 Entity disambiguation (via description) batch_6a3e9e99bdf081909934fab6490220d7 completed June 26, 2026, 3:45 p.m.
Created at: May 3, 2026, 3:59 p.m.