Triple

T16290794
Position Surface form Disambiguated ID Type / Status
Subject Sang et Or E395515 entity
Predicate hasColorTerm P48842 FINISHED
Object Sang
Sang is a French term meaning "blood," often used to denote a deep, vivid red color.
E1204910 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: Sang | Statement: [Sang et Or, hasColorTerm, Sang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sang
Context triple: [Sang et Or, hasColorTerm, Sang]
  • A. SANG
    SANG is the acronym for the Saudi Arabian National Guard, a key military and security force responsible for protecting the Saudi royal family, strategic facilities, and internal stability.
  • B. Sung
    Sung is the given name of actor Sung Kang, best known for his role as Han in the Fast & Furious film franchise.
  • C. Sangan
    Sangan is a town located in Pakistan’s Balochistan province within the Sibi District.
  • D. Sangatte
    Sangatte is a coastal commune in northern France on the English Channel, known for its proximity to the Channel Tunnel and the Cap Blanc-Nez cliffs.
  • E. Solung
    Solung is a major agricultural and socio-religious festival of the Adi community in Arunachal Pradesh, celebrated with rituals, dances, and feasting to invoke prosperity and good harvest.
  • 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: Sang
Triple: [Sang et Or, hasColorTerm, Sang]
Generated description
Sang is a French term meaning "blood," often used to denote a deep, vivid red color.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sang
Target entity description: Sang is a French term meaning "blood," often used to denote a deep, vivid red color.
  • A. SANG
    SANG is the acronym for the Saudi Arabian National Guard, a key military and security force responsible for protecting the Saudi royal family, strategic facilities, and internal stability.
  • B. Sung
    Sung is the given name of actor Sung Kang, best known for his role as Han in the Fast & Furious film franchise.
  • C. Sangan
    Sangan is a town located in Pakistan’s Balochistan province within the Sibi District.
  • D. Sangatte
    Sangatte is a coastal commune in northern France on the English Channel, known for its proximity to the Channel Tunnel and the Cap Blanc-Nez cliffs.
  • E. Solung
    Solung is a major agricultural and socio-religious festival of the Adi community in Arunachal Pradesh, celebrated with rituals, dances, and feasting to invoke prosperity and good harvest.
  • 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_69d87f22c7248190a54c949738441e2e completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2491821d0819086cffdd7551ba85a completed April 17, 2026, 2:52 p.m.
NED1 Entity disambiguation (via context triple) batch_6a001f97895081909f22ded3507afe14 completed May 10, 2026, 6:03 a.m.
NEDg Description generation batch_6a0020c8f904819090bea8655972fa85 completed May 10, 2026, 6:08 a.m.
NED2 Entity disambiguation (via description) batch_6a00213560588190850ab5a66fc43704 completed May 10, 2026, 6:09 a.m.
Created at: April 10, 2026, 5:05 a.m.