Triple

T25707494
Position Surface form Disambiguated ID Type / Status
Subject Five Find-Outers and Dog E644632 entity
Predicate appearsIn P795 FINISHED
Object The Mystery of the Strange Bundle
The Mystery of the Strange Bundle is one of Enid Blyton’s Five Find-Outers detective novels, in which the child sleuths investigate a puzzling case involving a bizarrely wrapped parcel.
E1695366 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: The Mystery of the Strange Bundle | Statement: [Five Find-Outers and Dog, appearsIn, The Mystery of the Strange Bundle]
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: The Mystery of the Strange Bundle
Triple: [Five Find-Outers and Dog, appearsIn, The Mystery of the Strange Bundle]
Generated description
The Mystery of the Strange Bundle is one of Enid Blyton’s Five Find-Outers detective novels, in which the child sleuths investigate a puzzling case involving a bizarrely wrapped parcel.

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_69e77e83c8ec8190bf52fcdac4838984 completed April 21, 2026, 1:41 p.m.
NER Named-entity recognition batch_69f5fc121e8081909775cb91f4a34906 completed May 2, 2026, 1:28 p.m.
NED1 Entity disambiguation (via context triple) batch_6a10cbf5bc648190a25fb6ff26889923 completed May 22, 2026, 9:34 p.m.
NEDg Description generation batch_6a10cd3856608190945e7ac95094ea09 completed May 22, 2026, 9:40 p.m.
NED2 Entity disambiguation (via description) batch_6a10ce00cda08190a1534b9ce1cf896a completed May 22, 2026, 9:43 p.m.
Created at: April 21, 2026, 9:06 p.m.