Triple

T28935464
Position Surface form Disambiguated ID Type / Status
Subject Harry Houdini E733901 entity
Predicate signatureAct P5573 FINISHED
Object upside-down straitjacket escape
The upside-down straitjacket escape is a famous Houdini stunt in which he was hoisted high above the ground and freed himself from a tightly fastened straitjacket while hanging inverted before large crowds.
E1843019 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: upside-down straitjacket escape | Statement: [Harry Houdini, signatureAct, upside-down straitjacket escape]
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: upside-down straitjacket escape
Triple: [Harry Houdini, signatureAct, upside-down straitjacket escape]
Generated description
The upside-down straitjacket escape is a famous Houdini stunt in which he was hoisted high above the ground and freed himself from a tightly fastened straitjacket while hanging inverted before large crowds.

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_69f05b0b49b08190b8994b339c7980f6 completed April 28, 2026, 7 a.m.
NER Named-entity recognition batch_69f65b56ac9c8190a688e82db0aa8427 completed May 2, 2026, 8:15 p.m.
NED1 Entity disambiguation (via context triple) batch_6a24ec3fb37c8190bfe249fee2a379db completed June 7, 2026, 3:57 a.m.
NEDg Description generation batch_6a24f3a02a4881909dfca1752009c390 completed June 7, 2026, 4:29 a.m.
NED2 Entity disambiguation (via description) batch_6a24f7d769e88190917a3690acdb3e73 completed June 7, 2026, 4:47 a.m.
Created at: April 28, 2026, 8:31 a.m.