Triple

T3208085
Position Surface form Disambiguated ID Type / Status
Subject Mumbai Harbour E67210 entity
Predicate hasPart P35 FINISHED
Object Nhava Sheva
Nhava Sheva, also known as Jawaharlal Nehru Port, is India’s largest container port located across the harbor from Mumbai.
 E355735 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: Nhava Sheva | Statement: [Mumbai Harbour, hasPart, Nhava Sheva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Nhava Sheva
Context triple: [Mumbai Harbour, hasPart, Nhava Sheva]
  • A. Ramat Gan
    Ramat Gan is a city in the Tel Aviv District of Israel, known for its diamond exchange district, business centers, and large urban park.
  • B. Kiryat Ono
    Kiryat Ono is a small suburban city in central Israel, located in the Tel Aviv metropolitan area.
  • C. Herzliya
    Herzliya is a coastal city in central Israel known as a high-tech and academic hub, home to major technology companies and institutions.
  • D. Givatayim
    Givatayim is a small, densely populated city in Israel’s Tel Aviv metropolitan area, known for its residential character and proximity to major urban centers.
  • E. Kiryat Tiv'on
    Kiryat Tiv'on is a town in northern Israel, near Haifa, known for its residential character and proximity to archaeological and natural sites.
  • 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: Nhava Sheva
Triple: [Mumbai Harbour, hasPart, Nhava Sheva]
Generated description
Nhava Sheva, also known as Jawaharlal Nehru Port, is India’s largest container port located across the harbor from Mumbai.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Nhava Sheva
Target entity description: Nhava Sheva, also known as Jawaharlal Nehru Port, is India’s largest container port located across the harbor from Mumbai.
  • A. Ramat Gan
    Ramat Gan is a city in the Tel Aviv District of Israel, known for its diamond exchange district, business centers, and large urban park.
  • B. Kiryat Ono
    Kiryat Ono is a small suburban city in central Israel, located in the Tel Aviv metropolitan area.
  • C. Herzliya
    Herzliya is a coastal city in central Israel known as a high-tech and academic hub, home to major technology companies and institutions.
  • D. Givatayim
    Givatayim is a small, densely populated city in Israel’s Tel Aviv metropolitan area, known for its residential character and proximity to major urban centers.
  • E. Kiryat Tiv'on
    Kiryat Tiv'on is a town in northern Israel, near Haifa, known for its residential character and proximity to archaeological and natural sites.
  • 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_69ad858ac36c81909962589cd277d6e2 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69adaa59888481908bdaefa1968d7f04 completed March 8, 2026, 4:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b34bafeea081908b0909dff919a4fc completed March 12, 2026, 11:26 p.m.
NEDg Description generation batch_69b34ff5a3608190bf8f33ae25b3d1ba completed March 12, 2026, 11:44 p.m.
NED2 Entity disambiguation (via description) batch_69b350b528e4819083497ecfaec5c80d completed March 12, 2026, 11:48 p.m.
Created at: March 8, 2026, 3:07 p.m.