Triple
T19832722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | katabasis |
E476502
|
entity |
| Predicate | involvesLocationType |
P76462
|
FINISHED |
| Object | underworld |
—
|
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: underworld | Statement: [katabasis, involvesLocationType, underworld]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: involvesLocationType Context triple: [katabasis, involvesLocationType, underworld]
-
A.
subjectLocationType
Indicates the type or category of location associated with the subject in the relationship.
-
B.
likelyLocatedIn
Indicates that an entity is probably situated within or associated with a particular location, though not with absolute certainty.
-
C.
involvedLocation
chosen
Indicates that an event, action, or relationship takes place in, or is significantly associated with, a particular location.
-
D.
hasLocationRole
Indicates that an entity holds or plays a specific role in relation to a particular location (e.g., origin, destination, storage site, or operational area).
-
E.
agingLocation
Indicates the place where an entity undergoes an aging process or is stored to age over time.
- 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_69d8e51c7c188190b926f3a2a7b5f881 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e656cf7e488190b4be28b5e7b363bf |
completed | April 20, 2026, 4:39 p.m. |
| PD | Predicate disambiguation | batch_69e5305bda388190a23b7191768107b1 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:50 p.m.