Triple
T30635441
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emily Prentiss |
E779828
|
entity |
| Predicate | hasComplexBackstory |
P184571
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Emily Prentiss, hasComplexBackstory, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasComplexBackstory Context triple: [Emily Prentiss, hasComplexBackstory, true]
-
A.
hasFictionalBackstory
Indicates that an entity is associated with an invented or imaginary narrative background rather than a real-world history.
-
B.
hasKeyFigureInBackstory
Indicates that an entity’s background narrative prominently features a particular individual who significantly influences or shapes that backstory.
-
C.
expandsBackstoryOf
Indicates that one entity provides additional background details or context that elaborate on the history or origins of another entity.
-
D.
hasMysteriousPast
Indicates that an entity possesses a past that is unknown, hidden, or only partially revealed, often implying secrets or unexplained events.
-
E.
hasComplexPast
chosen
Indicates that an entity has a history characterized by multiple significant, intricate, or difficult events or circumstances.
- 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_69f224a50ebc81909b961a94c7f66b12 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a0174e8b5b481908bf0c6d3d5b0f3b6 |
completed | May 11, 2026, 6:19 a.m. |
| PD | Predicate disambiguation | batch_6a01748d65248190ac3d9adfa9d0b274 |
completed | May 11, 2026, 6:17 a.m. |
Created at: April 29, 2026, 8:28 p.m.