Triple

T5150123
Position Surface form Disambiguated ID Type / Status
Subject 20th Maine Volunteer Infantry Regiment E116171 entity
Predicate casualtiesAtGettysburg P35438 FINISHED
Object over 30 percent of engaged strength 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: over 30 percent of engaged strength | Statement: [20th Maine Volunteer Infantry Regiment, casualtiesAtGettysburg, over 30 percent of engaged strength]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: casualtiesAtGettysburg
Context triple: [20th Maine Volunteer Infantry Regiment, casualtiesAtGettysburg, over 30 percent of engaged strength]
  • A. confederateCasualtiesAndLosses
    Indicates the number or extent of casualties and material losses suffered by Confederate forces in a conflict or engagement.
  • B. casualties
    Indicates that an event, action, or situation resulted in people being killed or injured.
  • C. UScasualties
    Indicates the number or occurrence of casualties suffered by the United States in a given conflict, event, or situation.
  • D. casualtiesAssociatedWithEvent chosen
    Indicates that certain casualties (deaths or injuries) are linked to, or resulted from, a specific event.
  • E. casualtiesEstimate
    Indicates an estimated number of people killed, injured, or otherwise harmed as a result of an event or incident.
  • 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_69bd4446c0e08190a7c29dc74976bf03 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd78d7f4d081908d59adcd86f52f1d completed March 20, 2026, 4:42 p.m.
PD Predicate disambiguation batch_69bd77ae2f10819098bb8939106e1281 completed March 20, 2026, 4:37 p.m.
Created at: March 20, 2026, 1:43 p.m.