Triple

T1776490
Position Surface form Disambiguated ID Type / Status
Subject Softsoap liquid hand soap E38991 entity
Predicate brandName P1500 FINISHED
Object Softsoap E38987 NE FINISHED

How this triple was built (2 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: Softsoap | Statement: [Softsoap liquid hand soap, brandName, Softsoap]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Softsoap
Context triple: [Softsoap liquid hand soap, brandName, Softsoap]
  • A. Softsoap chosen
    Softsoap is a popular personal care product line best known for its liquid hand soaps and body washes.
  • B. Soap
    Soap is a satirical American television sitcom that parodied daytime soap operas and became a cult classic for its controversial, boundary-pushing humor.
  • C. Shampoo
    "Shampoo" is a 1975 satirical romantic comedy film set on the eve of the 1968 U.S. presidential election, starring Warren Beatty as a Beverly Hills hairdresser entangled in complex romantic and social relationships.
  • D. Softsoap liquid hand soap
    Softsoap liquid hand soap is a widely sold brand of liquid hand soap known for its variety of scents and formulations for everyday household use.
  • E. Angel Soft
    Angel Soft is a popular American toilet paper brand known for its balance of softness, strength, and affordability.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a8862e61708190af97b9838cc3f5de completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa64b839608190b32bc041267458d5 completed March 6, 2026, 5:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69ada99a81c08190b602858708263193 completed March 8, 2026, 4:53 p.m.
Created at: March 4, 2026, 7:31 p.m.