Triple

T26394876

Position	Surface form	Disambiguated ID	Type / Status
Subject	Theodore Hall	`E663519`	entity
Predicate	intelligenceCodename	`P27308`	FINISHED
Object	MLAD MLAD was the Soviet intelligence codename assigned to American physicist and atomic spy Theodore Hall during his work on the Manhattan Project.	`E1722786`	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: MLAD | Statement: [Theodore Hall, intelligenceCodename, MLAD]

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: MLAD
Triple: [Theodore Hall, intelligenceCodename, MLAD]

Generated description

MLAD was the Soviet intelligence codename assigned to American physicist and atomic spy Theodore Hall during his work on the Manhattan Project.

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

Target predicate: intelligenceCodename
Context triple: [Theodore Hall, intelligenceCodename, MLAD]

A. codenameLetter
Indicates that one entity is the letter component of another entity’s codename.
B. securityCodename chosen
Indicates that an entity is assigned a specific codename used for security, confidentiality, or protective identification purposes.
C. codenameNumber
Indicates that an entity is assigned or associated with a specific codename identifier represented as a number.
D. relatedCodename
Indicates that one entity has an associated or connected codename that is contextually related to it.
E. codenameUser
Indicates that a user is assigned or associated with a particular codename.
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_69ee883823988190b418b111be28a44a`	completed	April 26, 2026, 9:48 p.m.
NER	Named-entity recognition	`batch_69f610c1b57081909b603c41b3c0e5e0`	completed	May 2, 2026, 2:57 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a119a850590819087b76e9ed16aee7e`	completed	May 23, 2026, 12:16 p.m.
NEDg	Description generation	`batch_6a119c71d29c81909bc7875bad89ce29`	completed	May 23, 2026, 12:24 p.m.
NED2	Entity disambiguation (via description)	`batch_6a119d54117c81909ec9709271172d7b`	completed	May 23, 2026, 12:28 p.m.
PD	Predicate disambiguation	`batch_69f5f800fa9c8190aab0962669fde8ac`	completed	May 2, 2026, 1:11 p.m.

Created at: April 26, 2026, 11:28 p.m.