Triple

T4663057
Position Surface form Disambiguated ID Type / Status
Subject Amber Heard E102779 entity
Predicate givenName P17 FINISHED
Object Amber
Amber is a feminine given name derived from the English word for the fossilized tree resin, often associated with a warm, golden color.
 E458626 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: Amber | Statement: [Amber Heard, givenName, Amber]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Amber
Context triple: [Amber Heard, givenName, Amber]
  • A. Amber
    Amber is a historic town near Jaipur in Rajasthan, India, renowned for its hilltop Amber Fort and rich Rajput architectural heritage.
  • B. Amber
    Amber is a character from the film "Green Room," a tense horror-thriller about a punk band trapped in a remote venue controlled by violent neo-Nazis.
  • C. Opal
    Opal is a precious gemstone renowned for its vibrant play-of-color and is especially associated with major deposits in Australia.
  • D. Opal
    Opal is a contactless smartcard-based public transport ticketing system used across New South Wales, Australia.
  • E. Zipolite
    Zipolite is a small, laid-back beach town on Mexico’s Oaxacan coast, known for its clothing-optional beach, bohemian vibe, and strong Pacific surf.
  • 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: Amber
Triple: [Amber Heard, givenName, Amber]
Generated description
Amber is a feminine given name derived from the English word for the fossilized tree resin, often associated with a warm, golden color.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Amber
Target entity description: Amber is a feminine given name derived from the English word for the fossilized tree resin, often associated with a warm, golden color.
  • A. Amber
    Amber is a character from the film "Green Room," a tense horror-thriller about a punk band trapped in a remote venue controlled by violent neo-Nazis.
  • B. Amber
    Amber is a historic town near Jaipur in Rajasthan, India, renowned for its hilltop Amber Fort and rich Rajput architectural heritage.
  • C. Opal
    Opal is a precious gemstone renowned for its vibrant play-of-color and is especially associated with major deposits in Australia.
  • D. Opal
    Opal is a contactless smartcard-based public transport ticketing system used across New South Wales, Australia.
  • E. Zipolite
    Zipolite is a small, laid-back beach town on Mexico’s Oaxacan coast, known for its clothing-optional beach, bohemian vibe, and strong Pacific surf.
  • 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_69bd43d9cba4819086c1ab1c2d9d2133 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd632d6150819085bab97021c0235a completed March 20, 2026, 3:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfafcd3908190aabf7975017ce337 completed March 21, 2026, 1:57 a.m.
NEDg Description generation batch_69bdfc7b84108190af39c7780f702745 completed March 21, 2026, 2:03 a.m.
NED2 Entity disambiguation (via description) batch_69bdfd3856b48190a44f49da5fde38f6 completed March 21, 2026, 2:06 a.m.
Created at: March 20, 2026, 1:15 p.m.