Triple

T1486837
Position Surface form Disambiguated ID Type / Status
Subject Jakarta E29483 entity
Predicate formerName P65 FINISHED
Object Sunda Kelapa
Sunda Kelapa is the historic old port area of Jakarta, Indonesia, known as a key trading hub in the region since precolonial times.
E169807 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: Sunda Kelapa | Statement: [Jakarta, formerName, Sunda Kelapa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sunda Kelapa
Context triple: [Jakarta, formerName, Sunda Kelapa]
  • A. Tanjung Priok
    Tanjung Priok is Indonesia’s busiest and largest seaport, serving as the main maritime gateway to Jakarta and the island of Java.
  • B. Pelabuhan Ratu
    Pelabuhan Ratu is a coastal town and bay in West Java, Indonesia, known for its scenic beaches, strong surf, and local fishing culture.
  • C. Port of Tanjung Emas
    The Port of Tanjung Emas is the main seaport serving Semarang and Central Java, Indonesia, handling regional cargo and passenger traffic along the northern coast of Java.
  • D. Batam Port
    Batam Port is a major Indonesian seaport on Batam Island that serves as a key maritime and logistics hub near the Singapore Strait.
  • E. Belawan Port
    Belawan Port is a major seaport and key maritime gateway for the city of Medan and the surrounding region in North Sumatra, Indonesia.
  • 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: Sunda Kelapa
Triple: [Jakarta, formerName, Sunda Kelapa]
Generated description
Sunda Kelapa is the historic old port area of Jakarta, Indonesia, known as a key trading hub in the region since precolonial times.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sunda Kelapa
Target entity description: Sunda Kelapa is the historic old port area of Jakarta, Indonesia, known as a key trading hub in the region since precolonial times.
  • A. Tanjung Priok
    Tanjung Priok is Indonesia’s busiest and largest seaport, serving as the main maritime gateway to Jakarta and the island of Java.
  • B. Pelabuhan Ratu
    Pelabuhan Ratu is a coastal town and bay in West Java, Indonesia, known for its scenic beaches, strong surf, and local fishing culture.
  • C. Port of Tanjung Emas
    The Port of Tanjung Emas is the main seaport serving Semarang and Central Java, Indonesia, handling regional cargo and passenger traffic along the northern coast of Java.
  • D. Batam Port
    Batam Port is a major Indonesian seaport on Batam Island that serves as a key maritime and logistics hub near the Singapore Strait.
  • E. Belawan Port
    Belawan Port is a major seaport and key maritime gateway for the city of Medan and the surrounding region in North Sumatra, Indonesia.
  • 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_69a498da82e08190ba833330d05f380f completed March 1, 2026, 7:51 p.m.
NER Named-entity recognition batch_69a4c6a3325881909bbc55efc04ad60f completed March 1, 2026, 11:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad15b5aa348190bf6d7a3177eacaff completed March 8, 2026, 6:22 a.m.
NEDg Description generation batch_69ad192ac37c819081aa4bb32e3564d8 completed March 8, 2026, 6:37 a.m.
NED2 Entity disambiguation (via description) batch_69ad19ab136081909c52731e346f2efb completed March 8, 2026, 6:39 a.m.
Created at: March 1, 2026, 8:12 p.m.