Triple

T14231688
Position Surface form Disambiguated ID Type / Status
Subject Sumpah Palapa E352765 entity
Predicate mentionedPlaces P10233 FINISHED
Object Haru
Haru was a historical polity or region in the Indonesian archipelago referenced in the 14th-century Javanese oath of Sumpah Palapa, associated with the Majapahit Empire’s sphere of influence.
 E1087859 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: Haru | Statement: [Sumpah Palapa, mentionedPlaces, Haru]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Haru
Context triple: [Sumpah Palapa, mentionedPlaces, Haru]
  • A. Haru
    Haru is the bumbling, well-meaning wannabe ninja protagonist played by Chris Farley in the comedy film "Beverly Hills Ninja."
  • B. Hara
    Hara is a Japanese surname borne by various notable figures in politics, arts, and sports.
  • C. Haruna
    Haruna was a Japanese Kongō-class fast battleship that served in the Imperial Japanese Navy during both World Wars and saw extensive action in the Pacific Theater.
  • D. Harumi
    Harumi is a waterfront district in Tokyo’s Chūō ward known for its high-rise residential towers and role in the Tokyo 2020 Olympic and Paralympic Village.
  • E. Teru
    Teru is a musical track featured on the album "Adam's Apple."
  • 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: Haru
Triple: [Sumpah Palapa, mentionedPlaces, Haru]
Generated description
Haru was a historical polity or region in the Indonesian archipelago referenced in the 14th-century Javanese oath of Sumpah Palapa, associated with the Majapahit Empire’s sphere of influence.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Haru
Target entity description: Haru was a historical polity or region in the Indonesian archipelago referenced in the 14th-century Javanese oath of Sumpah Palapa, associated with the Majapahit Empire’s sphere of influence.
  • A. Haru
    Haru is the bumbling, well-meaning wannabe ninja protagonist played by Chris Farley in the comedy film "Beverly Hills Ninja."
  • B. Hara
    Hara is a Japanese surname borne by various notable figures in politics, arts, and sports.
  • C. Haruna
    Haruna was a Japanese Kongō-class fast battleship that served in the Imperial Japanese Navy during both World Wars and saw extensive action in the Pacific Theater.
  • D. Harumi
    Harumi is a waterfront district in Tokyo’s Chūō ward known for its high-rise residential towers and role in the Tokyo 2020 Olympic and Paralympic Village.
  • E. Teru
    Teru is a musical track featured on the album "Adam's Apple."
  • 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_69d8278adc7c8190a9218d69bce3c4e6 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de622cdd6481908befa179a9675bb5 completed April 14, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd281bc67c81909bb09ee4a39a0b7f completed May 8, 2026, 12:02 a.m.
NEDg Description generation batch_69fd29ee7e0c819095bc48e54f825bc6 completed May 8, 2026, 12:10 a.m.
NED2 Entity disambiguation (via description) batch_69fd2aa5bf3c8190bb62ce780d417b7d completed May 8, 2026, 12:13 a.m.
Created at: April 10, 2026, 1:07 a.m.