Triple

T7275934
Position Surface form Disambiguated ID Type / Status
Subject Robert Indiana E163026 entity
Predicate notableWork P4 FINISHED
Object AHAVA
AHAVA is a famous Hebrew-language sculpture by American artist Robert Indiana that adapts his iconic LOVE design into the word for “love” in Hebrew.
 E653263 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: AHAVA | Statement: [Robert Indiana, notableWork, AHAVA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AHAVA
Context triple: [Robert Indiana, notableWork, AHAVA]
  • A. MUNA
    MUNA is a national museum in El Salvador dedicated to preserving and showcasing the country’s anthropological and cultural heritage.
  • B. Biotherm
    Biotherm is a French skincare brand known for its use of aquatic ingredients and scientifically driven formulas for face and body care.
  • C. DHC
    DHC is the commonly used abbreviation for the Delhi High Court, one of the principal high courts in India with jurisdiction over the National Capital Territory of Delhi.
  • D. Nexxus
    Nexxus is a professional hair care brand known for its salon-quality shampoos, conditioners, and styling products.
  • E. Huda Beauty
    Huda Beauty is a globally popular cosmetics brand founded by makeup artist and influencer Huda Kattan, known for its trend-setting makeup products and strong social media presence.
  • 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: AHAVA
Triple: [Robert Indiana, notableWork, AHAVA]
Generated description
AHAVA is a famous Hebrew-language sculpture by American artist Robert Indiana that adapts his iconic LOVE design into the word for “love” in Hebrew.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AHAVA
Target entity description: AHAVA is a famous Hebrew-language sculpture by American artist Robert Indiana that adapts his iconic LOVE design into the word for “love” in Hebrew.
  • A. MUNA
    MUNA is a national museum in El Salvador dedicated to preserving and showcasing the country’s anthropological and cultural heritage.
  • B. Biotherm
    Biotherm is a French skincare brand known for its use of aquatic ingredients and scientifically driven formulas for face and body care.
  • C. DHC
    DHC is the commonly used abbreviation for the Delhi High Court, one of the principal high courts in India with jurisdiction over the National Capital Territory of Delhi.
  • D. Nexxus
    Nexxus is a professional hair care brand known for its salon-quality shampoos, conditioners, and styling products.
  • E. Huda Beauty
    Huda Beauty is a globally popular cosmetics brand founded by makeup artist and influencer Huda Kattan, known for its trend-setting makeup products and strong social media presence.
  • 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_69c6885c5964819085b209701769877f completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6eb2f239c819097c1ac4d6de8b0e5 completed March 27, 2026, 8:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7db2c76fc81909632c7ee4e54f81c completed March 28, 2026, 1:44 p.m.
NEDg Description generation batch_69c7dc1469e08190a0b2b924884885e6 completed March 28, 2026, 1:48 p.m.
NED2 Entity disambiguation (via description) batch_69c7dca05ad081908e2036ba6c909c09 completed March 28, 2026, 1:50 p.m.
Created at: March 27, 2026, 2:59 p.m.