Triple

T36962972
Position Surface form Disambiguated ID Type / Status
Subject The Hound Pits Pub E914353 entity
Predicate associatedWithCharacter P1481 FINISHED
Object Admiral Havelock
Admiral Havelock is a key military leader and conspirator in the video game "Dishonored," central to the plot surrounding the Loyalist resistance.
E2206237 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: Admiral Havelock | Statement: [The Hound Pits Pub, associatedWithCharacter, Admiral Havelock]
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: Admiral Havelock
Triple: [The Hound Pits Pub, associatedWithCharacter, Admiral Havelock]
Generated description
Admiral Havelock is a key military leader and conspirator in the video game "Dishonored," central to the plot surrounding the Loyalist resistance.

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_69f76e8c498c8190b2842db80aea8b3b completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69f9ff0f80988190b9afefc8b4a0753d completed May 5, 2026, 2:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a3e8c27b940819093043d966aaf23c0 completed June 26, 2026, 2:26 p.m.
NEDg Description generation batch_6a3e994e3f588190bf16cab65967cb73 completed June 26, 2026, 3:22 p.m.
NED2 Entity disambiguation (via description) batch_6a3e99d4a5ec8190b0f451ee9d6127d7 completed June 26, 2026, 3:25 p.m.
Created at: May 3, 2026, 4:14 p.m.