Triple

T20061244
Position Surface form Disambiguated ID Type / Status
Subject Icade E499478 entity
Predicate tickerSymbol P1447 FINISHED
Object ICAD
ICAD is the stock market ticker symbol for Icade, a major French real estate investment and development company.
E1409040 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: ICAD | Statement: [Icade, tickerSymbol, ICAD]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ICAD
Context triple: [Icade, tickerSymbol, ICAD]
  • A. CICAD
    CICAD is the Inter-American Drug Abuse Control Commission, a specialized body of the Organization of American States that coordinates regional policies and programs to prevent and control drug abuse and related crimes in the Americas.
  • B. CAIDAS
    CAIDAS is a research center focused on advancing artificial intelligence and data science through interdisciplinary collaboration and innovation.
  • C. CACD
    CACD is the commonly used abbreviation for the United States District Court for the Central District of California, a federal trial court serving the central region of the state.
  • D. ICA
    ICA is a contemporary art museum in Philadelphia known for its innovative exhibitions and support of emerging artists.
  • E. ICA
    ICA is a leading global academic association dedicated to advancing the study and practice of communication through research, teaching, and professional collaboration.
  • 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: ICAD
Triple: [Icade, tickerSymbol, ICAD]
Generated description
ICAD is the stock market ticker symbol for Icade, a major French real estate investment and development company.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: ICAD
Target entity description: ICAD is the stock market ticker symbol for Icade, a major French real estate investment and development company.
  • A. CICAD
    CICAD is the Inter-American Drug Abuse Control Commission, a specialized body of the Organization of American States that coordinates regional policies and programs to prevent and control drug abuse and related crimes in the Americas.
  • B. CAIDAS
    CAIDAS is a research center focused on advancing artificial intelligence and data science through interdisciplinary collaboration and innovation.
  • C. CACD
    CACD is the commonly used abbreviation for the United States District Court for the Central District of California, a federal trial court serving the central region of the state.
  • D. ICA
    ICA is a contemporary art museum in Philadelphia known for its innovative exhibitions and support of emerging artists.
  • E. ICA
    ICA is a leading global academic association dedicated to advancing the study and practice of communication through research, teaching, and professional collaboration.
  • 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_69da6276bcf48190aabbf279192a5fb4 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6637601dc8190a07fc20844093cb7 completed April 20, 2026, 5:33 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0816108a408190a62065447c1045bb completed May 16, 2026, 7 a.m.
NEDg Description generation batch_6a0816fe5788819095736bd9464cfed5 completed May 16, 2026, 7:04 a.m.
NED2 Entity disambiguation (via description) batch_6a081798cb48819084ab456f79b68eb9 completed May 16, 2026, 7:07 a.m.
Created at: April 11, 2026, 3:38 p.m.