Triple

T25110318
Position Surface form Disambiguated ID Type / Status
Subject Manora, Karachi E628971 entity
Predicate hasPart P35 FINISHED
Object Manora Lighthouse
Manora Lighthouse is a historic coastal beacon near Karachi, Pakistan, that guides ships entering the Karachi Harbour.
E1670915 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: Manora Lighthouse | Statement: [Manora, Karachi, hasPart, Manora Lighthouse]
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: Manora Lighthouse
Triple: [Manora, Karachi, hasPart, Manora Lighthouse]
Generated description
Manora Lighthouse is a historic coastal beacon near Karachi, Pakistan, that guides ships entering the Karachi Harbour.

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_69e2ff3169d08190973b6061d5009abd completed April 18, 2026, 3:49 a.m.
NER Named-entity recognition batch_69f465767c48819086fa0573dca12276 completed May 1, 2026, 8:33 a.m.
NED1 Entity disambiguation (via context triple) batch_6a1067bb36d081909cd7c7ca35ea344d completed May 22, 2026, 2:27 p.m.
NEDg Description generation batch_6a1068d5ff248190b9efb77366147c26 completed May 22, 2026, 2:31 p.m.
NED2 Entity disambiguation (via description) batch_6a1069d0ba8c81908b38818567784552 completed May 22, 2026, 2:36 p.m.
Created at: April 18, 2026, 6:26 a.m.