Triple
T36547804
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | sinking of Beleriand |
E901180
|
entity |
| Predicate | survivorRegion |
P186040
|
FINISHED |
| Object | Lindon |
—
|
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: Lindon | Statement: [sinking of Beleriand, survivorRegion, Lindon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: survivorRegion Context triple: [sinking of Beleriand, survivorRegion, Lindon]
-
A.
remnantRegion
Indicates that a region is a leftover or remaining part of something that previously existed or was larger.
-
B.
occupiedRegion
Indicates that an entity has taken control of and is currently holding a specific geographic area or region.
-
C.
sinkingRegion
Indicates that a region is undergoing downward movement or subsidence, typically becoming lower relative to surrounding areas or a reference level.
-
D.
bulkRegion
Indicates a relationship where something pertains to, occupies, or defines a primary mass or volume region of an object or space, as opposed to its surface or boundary.
-
E.
formationRegion
Indicates the place or area where something originates, is created, or comes into being.
- F. None of above. chosen
Provenance (4 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_69f76e61217081908b79d610fe67b013 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c83f5960819089610ed39c839678 |
completed | May 3, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69f7c477a4d481908f52e55b6688f60c |
completed | May 3, 2026, 9:56 p.m. |
| PDg | Predicate description generation | batch_69f7c776b4088190bef550c869da530d |
completed | May 3, 2026, 10:08 p.m. |
Created at: May 3, 2026, 4:11 p.m.