Triple
T10808212
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boo Radley |
E255022
|
entity |
| Predicate | rumoredTo |
P28032
|
FINISHED |
| Object | stabbed his father with scissors |
—
|
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: stabbed his father with scissors | Statement: [Boo Radley, rumoredTo, stabbed his father with scissors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rumoredTo Context triple: [Boo Radley, rumoredTo, stabbed his father with scissors]
-
A.
rumoredTarget
Indicates that an entity is believed or speculated, based on rumor or unconfirmed information, to be the intended target of another entity or action.
-
B.
believedTo
Indicates that one entity holds a belief or conviction about the truth, existence, or properties of another entity or proposition.
-
C.
rumorContent
chosen
Indicates that the associated information specifies the subject matter or details contained within a particular rumor.
-
D.
hasSequelRumors
Indicates that there are rumors or unconfirmed reports suggesting a sequel exists or may be produced for the referenced work.
-
E.
hasBeenSpeculatedToBe
Indicates that something has been suggested or hypothesized, without firm evidence, to possibly be or correspond to something else.
- 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_69d6aa61c15c8190a1839550c56e75e1 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d733b506488190921e6a1f4168dd9e |
completed | April 9, 2026, 5:05 a.m. |
| PD | Predicate disambiguation | batch_69d6f3188f00819094ee8d65b187a333 |
completed | April 9, 2026, 12:30 a.m. |
Created at: April 8, 2026, 9:18 p.m.