Triple
T24761742
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deathly Hallows |
E619462
|
entity |
| Predicate | grantIfUnited |
P157099
|
FINISHED |
| Object | ability to recall the dead |
—
|
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: ability to recall the dead | Statement: [Deathly Hallows, grantIfUnited, ability to recall the dead]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: grantIfUnited Context triple: [Deathly Hallows, grantIfUnited, ability to recall the dead]
-
A.
grantIfUnited
chosen
Indicates that a grant or permission is given only when the relevant parties or components are united or acting as one.
-
B.
unites
Indicates that one entity brings together multiple entities into a single, cohesive whole or shared state.
-
C.
governingUnion
Indicates that one political or administrative entity serves as the primary governing authority over a union or collective of entities.
-
D.
confirmedUnionWith
Indicates that a previously proposed or potential union between entities has been formally verified and accepted as established.
-
E.
allowsCoalitionGovernments
Indicates that a political system or rule permits the formation of governments composed of multiple cooperating parties sharing executive power.
- 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_69e2fabbea94819092ed41348909622f |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f42d9000b8819081ea2605f3c193d6 |
completed | May 1, 2026, 4:35 a.m. |
| PD | Predicate disambiguation | batch_69f420f471a0819095a6cd24ed8f7476 |
completed | May 1, 2026, 3:41 a.m. |
Created at: April 18, 2026, 4:27 a.m.