Triple

T26305979
Position Surface form Disambiguated ID Type / Status
Subject Shabwah Governorate E661681 entity
Predicate hasPort P35 FINISHED
Object Bir Ali (coastal area)
Bir Ali is a coastal area and port town in Yemen known for its natural harbor and beaches along the Arabian Sea.
 E1718148 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: Bir Ali (coastal area) | Statement: [Shabwah Governorate, hasPort, Bir Ali (coastal area)]
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: Bir Ali (coastal area)
Triple: [Shabwah Governorate, hasPort, Bir Ali (coastal area)]
Generated description
Bir Ali is a coastal area and port town in Yemen known for its natural harbor and beaches along the Arabian Sea.

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_69ee812dacfc81908484aade9120fba9 completed April 26, 2026, 9:18 p.m.
NER Named-entity recognition batch_69f60ee2f18481908de53cc9872e96f4 completed May 2, 2026, 2:49 p.m.
NED1 Entity disambiguation (via context triple) batch_6a118fd048b48190b2cdc48f0c766067 completed May 23, 2026, 11:30 a.m.
NEDg Description generation batch_6a11908b60208190947e35ec81b2db01 completed May 23, 2026, 11:33 a.m.
NED2 Entity disambiguation (via description) batch_6a11918caf0c8190bf907ad2c258a8c4 completed May 23, 2026, 11:37 a.m.
Created at: April 26, 2026, 10:18 p.m.