Triple

T11729497
Position Surface form Disambiguated ID Type / Status
Subject lewisite E278861 entity
Predicate antidote P4524 FINISHED
Object British anti-Lewisite
British anti-Lewisite is a chelating agent and medical antidote primarily used to treat poisoning by arsenic-based chemical warfare agents and heavy metals.
E942092 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: British anti-Lewisite | Statement: [lewisite, antidote, British anti-Lewisite]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: British anti-Lewisite
Context triple: [lewisite, antidote, British anti-Lewisite]
  • A. Fleming
    Fleming is a surname most famously associated with Ian Fleming, the British author who created the James Bond spy novels.
  • B. Coombs
    Coombs is the surname of Princess Claire of Belgium, a member of the Belgian royal family originally from the United Kingdom.
  • C. Coombs
    Coombs is a small rural community on central Vancouver Island in British Columbia, Canada, known for its popular Old Country Market and quirky “goats on the roof” attraction.
  • D. Balemartine
    Balemartine is a small coastal village located on the island of Tiree in Scotland’s Inner Hebrides.
  • E. Wessely
    Wessely is a Jewish family name most notably associated with the 18th-century Haskalah (Jewish Enlightenment) figure Naphtali Herz Wessely.
  • 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: British anti-Lewisite
Triple: [lewisite, antidote, British anti-Lewisite]
Generated description
British anti-Lewisite is a chelating agent and medical antidote primarily used to treat poisoning by arsenic-based chemical warfare agents and heavy metals.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: British anti-Lewisite
Target entity description: British anti-Lewisite is a chelating agent and medical antidote primarily used to treat poisoning by arsenic-based chemical warfare agents and heavy metals.
  • A. Fleming
    Fleming is a surname most famously associated with Ian Fleming, the British author who created the James Bond spy novels.
  • B. Coombs
    Coombs is the surname of Princess Claire of Belgium, a member of the Belgian royal family originally from the United Kingdom.
  • C. Coombs
    Coombs is a small rural community on central Vancouver Island in British Columbia, Canada, known for its popular Old Country Market and quirky “goats on the roof” attraction.
  • D. Balemartine
    Balemartine is a small coastal village located on the island of Tiree in Scotland’s Inner Hebrides.
  • E. Wessely
    Wessely is a Jewish family name most notably associated with the 18th-century Haskalah (Jewish Enlightenment) figure Naphtali Herz Wessely.
  • 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_69d6aaffec6881908bead509e8621742 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a4d80ef881908cab956787ab07fd completed April 10, 2026, 7:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69ef83f98fc481908015df3c4e5d7ed3 completed April 27, 2026, 3:42 p.m.
NEDg Description generation batch_69ef9b68309081909f3f614efeeb2ab1 completed April 27, 2026, 5:22 p.m.
NED2 Entity disambiguation (via description) batch_69efd6aba82c81909ff22e6b26db3cfe completed April 27, 2026, 9:35 p.m.
Created at: April 8, 2026, 9:41 p.m.