Triple
T31491909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maaza Mengiste |
E803427
|
entity |
| Predicate | Beneath the Lion’s Gaze_setting |
P20834
|
FINISHED |
| Object | Addis Ababa |
—
|
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: Addis Ababa | Statement: [Maaza Mengiste, Beneath the Lion’s Gaze_setting, Addis Ababa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Beneath the Lion’s Gaze_setting Context triple: [Maaza Mengiste, Beneath the Lion’s Gaze_setting, Addis Ababa]
-
A.
Beneath the Lion’s Gaze_subject
Indicates that the subject is the work titled "Beneath the Lion’s Gaze" (e.g., a book, artwork, or similar creative entity).
-
B.
Beneath the Lion’s Gaze_theme
Indicates the central topics, ideas, or emotional concerns explored in "Beneath the Lion’s Gaze."
-
C.
Beneath the Lion’s Gaze_recognition
Indicates that an entity acknowledges, identifies, or gives formal attention to the work titled "Beneath the Lion’s Gaze."
-
D.
placeOfSetting
chosen
Indicates the location or environment where an event, scene, or situation takes place.
-
E.
جایگاه
Indicates a positional or hierarchical relationship specifying the place, rank, or status of one entity relative to others.
- 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_69f348ca04508190ba9379b5329dfd75 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca3dedc81908b519d53d2909868 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 30, 2026, 9:38 p.m.