Triple

T37561741

Position	Surface form	Disambiguated ID	Type / Status
Subject	John Steele (paratrooper)	`E933839`	entity
Predicate	entangledOn	`P91259`	FINISHED
Object	church steeple of Sainte-Mère-Église The church steeple of Sainte-Mère-Église is a historic Normandy landmark famous for the D-Day incident in which American paratrooper John Steele became snagged on it during the 1944 Allied invasion.	`E2233452`	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: church steeple of Sainte-Mère-Église | Statement: [John Steele (paratrooper), entangledOn, church steeple of Sainte-Mère-Église]

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: church steeple of Sainte-Mère-Église
Triple: [John Steele (paratrooper), entangledOn, church steeple of Sainte-Mère-Église]

Generated description

The church steeple of Sainte-Mère-Église is a historic Normandy landmark famous for the D-Day incident in which American paratrooper John Steele became snagged on it during the 1944 Allied invasion.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: entangledOn
Context triple: [John Steele (paratrooper), entangledOn, church steeple of Sainte-Mère-Église]

A. entangledWith
Indicates a mutual state in which two or more entities are so interconnected that a change or condition in one inherently affects or constrains the other(s).
B. canBeEntangledIn chosen
Indicates that one entity is capable of becoming physically or conceptually caught, intertwined, or ensnared within another entity or situation.
C. engagedOn
Indicates that two entities are committed to be married to each other as of a specific date or point in time.
D. engagedTo
Indicates that two entities are formally committed to marry each other.
E. bondedWith
Indicates that two entities are joined by a strong, enduring connection or attachment, whether emotional, social, or structural.
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_69f76ecb4acc8190b53f96d0b013e415`	completed	May 3, 2026, 3:50 p.m.
NER	Named-entity recognition	`batch_69fba61dff5081909fec88a7aeb0c8a1`	completed	May 6, 2026, 8:35 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a409f1848788190aafc58fb707829b7`	completed	June 28, 2026, 4:12 a.m.
NEDg	Description generation	`batch_6a40a0535cc08190bb21fcc94d768e0b`	completed	June 28, 2026, 4:17 a.m.
NED2	Entity disambiguation (via description)	`batch_6a40a1008abc8190a2861afb9a6bac4f`	completed	June 28, 2026, 4:20 a.m.
PD	Predicate disambiguation	`batch_69fba350e9a8819095893229d9643572`	completed	May 6, 2026, 8:23 p.m.

Created at: May 3, 2026, 4:17 p.m.