Triple
T36557548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haradwaith |
E901735
|
entity |
| Predicate | partiallyOverlapsWith |
P1867
|
FINISHED |
| Object | Harad |
—
|
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: Harad | Statement: [Haradwaith, partiallyOverlapsWith, Harad]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partiallyOverlapsWith Context triple: [Haradwaith, partiallyOverlapsWith, Harad]
-
A.
overlapsWith
chosen
Indicates that two entities share a common part or region in space, time, or extent, but neither is completely contained within the other.
-
B.
partiallyOn
Indicates that one entity rests or extends over another such that only a portion of its area, volume, or length is supported or in contact.
-
C.
isPartially
Indicates that one entity is included within another to some extent, but not completely or fully.
-
D.
partiallyEnclosed
Indicates that one entity surrounds or covers another entity to some extent, but not completely.
-
E.
partiallyCorrespondsTo
Indicates that one entity matches or aligns with another entity only in some aspects, segments, or components, rather than fully or exactly.
- 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_69f76e634e9481908c9ba1b87ab87c26 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fd02680d948190a3463fb119ba8556 |
completed | May 7, 2026, 9:21 p.m. |
| PD | Predicate disambiguation | batch_69fcf89c69b4819082bbc564bd15137d |
completed | May 7, 2026, 8:39 p.m. |
Created at: May 3, 2026, 4:11 p.m.