Triple

T35628949
Position Surface form Disambiguated ID Type / Status
Subject UNSC Marine Corps E1029532 entity
Predicate hasSubdivision P747 FINISHED
Object UNSC Marine Corps Force Recon
The UNSC Marine Corps Force Recon is an elite special operations unit in the Halo universe, specializing in deep reconnaissance, direct action, and high-risk missions behind enemy lines.
E2149579 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: UNSC Marine Corps Force Recon | Statement: [UNSC Marine Corps, hasSubdivision, UNSC Marine Corps Force Recon]
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: UNSC Marine Corps Force Recon
Triple: [UNSC Marine Corps, hasSubdivision, UNSC Marine Corps Force Recon]
Generated description
The UNSC Marine Corps Force Recon is an elite special operations unit in the Halo universe, specializing in deep reconnaissance, direct action, and high-risk missions behind enemy lines.

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_69f76e07bb0c8190968ea2d836fc42c9 completed May 3, 2026, 3:47 p.m.
NER Named-entity recognition batch_69f79f18160c81909e3a1ef204a39d34 completed May 3, 2026, 7:16 p.m.
NED1 Entity disambiguation (via context triple) batch_6a38684ce02c8190bb6fcf1874dc245d completed June 21, 2026, 10:40 p.m.
NEDg Description generation batch_6a386913196c81908274a2e909d943b8 completed June 21, 2026, 10:43 p.m.
NED2 Entity disambiguation (via description) batch_6a3869ef06088190a5e72b39204adf85 completed June 21, 2026, 10:47 p.m.
Created at: May 3, 2026, 4:05 p.m.