Triple
T37514016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tomb of Rakkis |
E932586
|
entity |
| Predicate | associatedWithLoreTopic |
P107052
|
FINISHED |
| Object | history of Westmarch |
—
|
LITERAL 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: history of Westmarch | Statement: [Tomb of Rakkis, associatedWithLoreTopic, history of Westmarch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithLoreTopic Context triple: [Tomb of Rakkis, associatedWithLoreTopic, history of Westmarch]
-
A.
associatedTale
Indicates that one entity is linked or connected to a particular tale, story, or narrative.
-
B.
associatedWithSubject
chosen
Indicates a general relationship or connection between an entity and a subject, without specifying the exact nature of that association.
-
C.
hasLoreRole
Indicates that an entity holds a specific narrative, mythological, or story-related role in relation to another entity or context.
-
D.
associatedWithAuthorTheme
Indicates a relationship where an author is linked to, or characterized by, a particular theme in their work or thought.
-
E.
seriesLore
Indicates that one entity provides backstory, world-building, or canonical background information that enriches the overarching narrative of a series in which the other entity appears.
- F. None of above.
Provenance (3 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_69f76ec730988190b5aa4f9cb9afd518 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1553e08190bb7424c448cb1f33 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:17 p.m.