Triple

T35298576

Position	Surface form	Disambiguated ID	Type / Status
Subject	Moiraine Damodred	`E1019442`	entity
Predicate	laterBondedTo	`P68132`	FINISHED
Object	Thom Merrilin Thom Merrilin is a skilled gleeman and former court bard in Robert Jordan's The Wheel of Time series, known for his sharp wit, deadly skill with knives, and complex ties to the royal courts of several nations.	`E2134893`	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: Thom Merrilin | Statement: [Moiraine Damodred, laterBondedTo, Thom Merrilin]

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: Thom Merrilin
Triple: [Moiraine Damodred, laterBondedTo, Thom Merrilin]

Generated description

Thom Merrilin is a skilled gleeman and former court bard in Robert Jordan's *The Wheel of Time* series, known for his sharp wit, deadly skill with knives, and complex ties to the royal courts of several nations.

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

Target predicate: laterBondedTo
Context triple: [Moiraine Damodred, laterBondedTo, Thom Merrilin]

A. bondedWith chosen
Indicates that two entities are joined by a strong, enduring connection or attachment, whether emotional, social, or structural.
B. pairBond
Indicates a long-term, typically exclusive social or reproductive partnership formed between two individuals.
C. matedWith
Indicates that two entities have engaged in mating or reproductive pairing with each other.
D. laterRelationshipWith
Indicates that one entity has a relationship with another that occurs at a later time relative to some reference point or prior relationship.
E. bondedWithSpecies
Indicates a relationship where an entity has formed a close, enduring bond or attachment with a particular species.
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_69f76de7eedc8190a3bdc64ebbc05b42`	completed	May 3, 2026, 3:46 p.m.
NER	Named-entity recognition	`batch_6a0062e6bd788190a7b4f3e5befb5cbb`	completed	May 10, 2026, 10:50 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a3819e7ce3c8190a3e68b725ce52848`	completed	June 21, 2026, 5:05 p.m.
NEDg	Description generation	`batch_6a381a89da088190b3b7e52b0531b692`	completed	June 21, 2026, 5:08 p.m.
NED2	Entity disambiguation (via description)	`batch_6a381b3c8ecc8190a22b608d4cb29b2a`	completed	June 21, 2026, 5:11 p.m.
PD	Predicate disambiguation	`batch_6a0061989d188190b4815b2de3e8676f`	completed	May 10, 2026, 10:44 a.m.

Created at: May 3, 2026, 4:03 p.m.