Triple
T32876287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Haunted Palace |
E840935
|
entity |
| Predicate | titlePoemAuthor |
P36356
|
FINISHED |
| Object | Edgar Allan Poe |
—
|
NE NERFINISHED |
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: Edgar Allan Poe | Statement: [The Haunted Palace, titlePoemAuthor, Edgar Allan Poe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titlePoemAuthor Context triple: [The Haunted Palace, titlePoemAuthor, Edgar Allan Poe]
-
A.
poemAuthor
chosen
Indicates that one entity is the author or creator of a poem represented by the other entity.
-
B.
poetAssociated
Indicates a relationship where a poet is connected or linked to another entity, such as a work, place, movement, or person, through relevance, collaboration, influence, or affiliation.
-
C.
hasPoemTitleReference
Indicates that one entity (such as a work, discussion, or reference) explicitly refers to or cites the title of a poem.
-
D.
associatedWithPoem
Indicates a relationship in which an entity is connected or linked to a particular poem, such as by authorship, subject, reference, or contextual association.
-
E.
titleSongComposer
Indicates that one entity is the composer of the title song associated with another entity (such as a film, show, or album).
- 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_69f349436ee88190b72ee12d0f3f508e |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fedfd913f48190bdcd450980868d9a |
completed | May 9, 2026, 7:18 a.m. |
| PD | Predicate disambiguation | batch_69fedf58c6e88190821a7156054c9086 |
completed | May 9, 2026, 7:16 a.m. |
Created at: May 1, 2026, 1:18 a.m.