Triple

T25814553
Position Surface form Disambiguated ID Type / Status
Subject Prince Mohammad bin Abdulaziz International Airport E650212 entity
Predicate servesPilgrimsTravelingTo P74993 FINISHED
Object Medina
Medina is Islam’s second holiest city in Saudi Arabia, revered as the burial place of the Prophet Muhammad and a major destination for Muslim pilgrims.
E28127 NE FINISHED

How this triple was built (3 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: Medina | Statement: [Prince Mohammad bin Abdulaziz International Airport, servesPilgrimsTravelingTo, Medina]
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: Medina
Triple: [Prince Mohammad bin Abdulaziz International Airport, servesPilgrimsTravelingTo, Medina]
Generated description
Medina is Islam’s second holiest city in Saudi Arabia, revered as the burial place of the Prophet Muhammad and a major destination for Muslim pilgrims.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: servesPilgrimsTravelingTo
Context triple: [Prince Mohammad bin Abdulaziz International Airport, servesPilgrimsTravelingTo, Medina]
  • A. servesPilgrimTrafficTo chosen
    Indicates that a location or entity functions as a route, hub, or provider facilitating the movement or flow of pilgrim traffic to a specified destination.
  • B. servesPilgrimageTrafficFrom
    Indicates that a location or facility accommodates or handles pilgrimage-related traffic originating from a specified place.
  • C. hasPilgrims
    Indicates that an entity is associated with or contains pilgrims, typically as visitors, members, or participants in a pilgrimage.
  • D. servesTravelersTo
    Indicates a relationship where one entity provides services, assistance, or accommodations specifically directed toward travelers heading to a particular destination.
  • E. hasPilgrimsLodgingNearby
    Indicates that there is lodging available in close proximity for pilgrims associated with the referenced entity.
  • F. None of above.

Provenance (6 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_69e7ab35d264819095367f7e80c983ff completed April 21, 2026, 4:52 p.m.
NER Named-entity recognition batch_69f6e6029a10819098ff21f58079e70e completed May 3, 2026, 6:06 a.m.
NED1 Entity disambiguation (via context triple) batch_6a11ae901a3481909860d13535ab3a4a completed May 23, 2026, 1:41 p.m.
NEDg Description generation batch_6a11af9c1be081909d2e461e3da596d6 completed May 23, 2026, 1:46 p.m.
NED2 Entity disambiguation (via description) batch_6a11b051d328819090f947755dda4cfc completed May 23, 2026, 1:49 p.m.
PD Predicate disambiguation batch_69f6e3d5e8188190b1e1c2e5d1b77031 completed May 3, 2026, 5:57 a.m.
Created at: April 22, 2026, 7:13 a.m.