Triple
T1988357
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Black Stone |
E43191
|
entity |
| Predicate | numberOfFragments |
P20105
|
FINISHED |
| Object | several smaller pieces |
—
|
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: several smaller pieces | Statement: [Black Stone, numberOfFragments, several smaller pieces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfFragments Context triple: [Black Stone, numberOfFragments, several smaller pieces]
-
A.
numberOfFragmentsApprox
chosen
Indicates an approximate count of how many fragments or pieces are associated with the subject.
-
B.
hasFragments
Indicates that an entity is composed of, contains, or is associated with one or more smaller constituent parts or pieces.
-
C.
numberOfSpans
Indicates the total count of distinct spans or segments associated with an entity or within a specified context.
-
D.
maximumNumberOfSegments
Indicates the greatest allowable or observed count of discrete segments into which something can be or is divided.
-
E.
numberOfTracks
Indicates the quantity of tracks associated with a given entity.
- 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_69a88713ddc88190a969715658ebe7a8 |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb8ee02dc81908fec9fd8df7a4f40 |
completed | March 7, 2026, 5:34 a.m. |
| PD | Predicate disambiguation | batch_69abb79ad6888190be99943a9c73cf3e |
completed | March 7, 2026, 5:28 a.m. |
Created at: March 4, 2026, 7:37 p.m.