Triple
T37350665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | House of Black tapestry |
E927311
|
entity |
| Predicate | seenByCharacter |
P124583
|
FINISHED |
| Object | Harry Potter |
—
|
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: Harry Potter | Statement: [House of Black tapestry, seenByCharacter, Harry Potter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seenByCharacter Context triple: [House of Black tapestry, seenByCharacter, Harry Potter]
-
A.
visitedByCharacter
Indicates that a location or place is visited or physically gone to by a specific character.
-
B.
seenOn
chosen
Indicates that one entity has been visually observed or noticed on, within, or in association with another entity.
-
C.
exposedByCharacter
Indicates that one character reveals, uncovers, or discloses something about another character or their actions.
-
D.
seenFrom
Indicates that one entity is visible or can be observed from the vantage point or location of another entity.
-
E.
unseenCharacter
Indicates that a character exists in the narrative or context but does not appear directly or visibly in the current scene or depiction.
- 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_69f76eb5e034819088e53ab5b7909a68 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb8c38a9688190be524246f5682107 |
completed | May 6, 2026, 6:45 p.m. |
| PD | Predicate disambiguation | batch_69fb5a9c6e0481908565bd849e869b24 |
completed | May 6, 2026, 3:13 p.m. |
Created at: May 3, 2026, 4:16 p.m.