Triple

T33083750
Position Surface form Disambiguated ID Type / Status
Subject John of Ibelin, Lord of Beirut E846574 entity
Predicate child P120 FINISHED
Object Guy of Ibelin
Guy of Ibelin was a 13th-century nobleman of the influential Ibelin family in the Crusader states, known primarily as a younger son of John of Ibelin, the prominent Lord of Beirut.
E2079354 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: Guy of Ibelin | Statement: [John of Ibelin, Lord of Beirut, child, Guy of Ibelin]
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: Guy of Ibelin
Triple: [John of Ibelin, Lord of Beirut, child, Guy of Ibelin]
Generated description
Guy of Ibelin was a 13th-century nobleman of the influential Ibelin family in the Crusader states, known primarily as a younger son of John of Ibelin, the prominent Lord of Beirut.

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_69f34954d46c8190a04a159cc5f99efd completed April 30, 2026, 12:21 p.m.
NER Named-entity recognition batch_69f6d61f114081908d17a5b53ecc14b7 completed May 3, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_6a36a00d67ac8190ab5456a3b1be57f4 completed June 20, 2026, 2:13 p.m.
NEDg Description generation batch_6a36a22e26c48190bef8db32655615fb completed June 20, 2026, 2:22 p.m.
NED2 Entity disambiguation (via description) batch_6a36a2988274819080706c25fef8b0eb completed June 20, 2026, 2:24 p.m.
Created at: May 1, 2026, 1:26 a.m.