Triple
T36817832
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fangorn Forest |
E909793
|
entity |
| Predicate | earlierExtent |
P86452
|
FINISHED |
| Object | once much larger in earlier ages |
—
|
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: once much larger in earlier ages | Statement: [Fangorn Forest, earlierExtent, once much larger in earlier ages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earlierExtent Context triple: [Fangorn Forest, earlierExtent, once much larger in earlier ages]
-
A.
originalExtent
chosen
Indicates the total size or scope that something initially had before any reduction, alteration, or loss.
-
B.
earlierNumber
Indicates that one numerical value occurs or is positioned before another in an ordered sequence or scale.
-
C.
eezExtent
Indicates the geographic area or spatial coverage of a country's exclusive economic zone (EEZ).
-
D.
earlierStatus
Indicates that one status or condition occurred or was valid before another status in time.
-
E.
currentExtentDesignated
Indicates that the currently applicable spatial or conceptual extent of something has been formally defined or designated.
- 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_69f76e7dd13c81908c60b05adb49eeb5 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcf36d2894819089b7db8e91b63c9d |
completed | May 7, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69fcf25c0a108190bfa823474098640b |
completed | May 7, 2026, 8:13 p.m. |
Created at: May 3, 2026, 4:13 p.m.