Triple

T19773030
Position Surface form Disambiguated ID Type / Status
Subject Ibrance E474934 entity
Predicate isUsedInCombinationWith P4791 FINISHED
Object letrozole
Letrozole is an oral aromatase inhibitor used primarily in the treatment of hormone receptor–positive breast cancer in postmenopausal women.
 E1394318 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: letrozole | Statement: [Ibrance, isUsedInCombinationWith, letrozole]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: letrozole
Context triple: [Ibrance, isUsedInCombinationWith, letrozole]
  • A. Lethenteron
    Lethenteron is a genus of jawless, eel-like lampreys found primarily in freshwater and coastal regions of the Northern Hemisphere.
  • B. Enovid
    Enovid was the first commercially available oral contraceptive pill, introduced in the 1960s and widely recognized for revolutionizing birth control and reproductive health.
  • C. danazol
    Danazol is a synthetic androgen used primarily to treat endometriosis, fibrocystic breast disease, and hereditary angioedema.
  • D. Giprostal
    Giprostal was a prominent Soviet-era design institute specializing in the planning and engineering of metallurgical and industrial facilities.
  • E. Contandin
    Contandin is the real surname of the famous French actor and comedian Fernandel.
  • 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: letrozole
Triple: [Ibrance, isUsedInCombinationWith, letrozole]
Generated description
Letrozole is an oral aromatase inhibitor used primarily in the treatment of hormone receptor–positive breast cancer in postmenopausal women.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: letrozole
Target entity description: Letrozole is an oral aromatase inhibitor used primarily in the treatment of hormone receptor–positive breast cancer in postmenopausal women.
  • A. Lethenteron
    Lethenteron is a genus of jawless, eel-like lampreys found primarily in freshwater and coastal regions of the Northern Hemisphere.
  • B. Enovid
    Enovid was the first commercially available oral contraceptive pill, introduced in the 1960s and widely recognized for revolutionizing birth control and reproductive health.
  • C. danazol
    Danazol is a synthetic androgen used primarily to treat endometriosis, fibrocystic breast disease, and hereditary angioedema.
  • D. Giprostal
    Giprostal was a prominent Soviet-era design institute specializing in the planning and engineering of metallurgical and industrial facilities.
  • E. Contandin
    Contandin is the real surname of the famous French actor and comedian Fernandel.
  • 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_69d8e51a43a08190956bc6df13c91a77 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6535e450c8190a2628245ae0d0bd3 completed April 20, 2026, 4:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07bd76afe08190b958bd49acf21c4a completed May 16, 2026, 12:42 a.m.
NEDg Description generation batch_6a07be5426c48190bb7b0fc315fa2f6a completed May 16, 2026, 12:46 a.m.
NED2 Entity disambiguation (via description) batch_6a07bf9682fc8190a33ea75dba8d88d6 completed May 16, 2026, 12:51 a.m.
Created at: April 10, 2026, 1:48 p.m.