Triple
T8932789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prince Johnson |
E212696
|
entity |
| Predicate | positionOnRecord |
P86259
|
FINISHED |
| Object | has defended his actions during the civil war |
—
|
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: has defended his actions during the civil war | Statement: [Prince Johnson, positionOnRecord, has defended his actions during the civil war]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionOnRecord Context triple: [Prince Johnson, positionOnRecord, has defended his actions during the civil war]
-
A.
positionOn
Indicates that one entity is located on top of or at a specific place along the surface or extent of another entity.
-
B.
positionOnRemix
Indicates the specific role or placement an entity has within a remix version of a work or composition.
-
C.
positionOnPast
Indicates that one entity occupied a specific position or location relative to another entity at some point in the past.
-
D.
playingPosition
Indicates the specific role or position an individual occupies while participating in a game or sport.
-
E.
discPosition
Indicates the spatial or ordinal placement of a disc relative to a reference point or within a set or structure.
- 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_69ca8395c438819087d7cb844ab5990c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc668e5c108190b08f9cd6b4fd4a8b |
completed | April 1, 2026, 12:27 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed3286c8190a21de2ee11f2639f |
completed | March 31, 2026, 11:54 p.m. |
| PDg | Predicate description generation | batch_69cc608331f88190bcb500ff63527f8a |
completed | April 1, 2026, 12:02 a.m. |
Created at: March 30, 2026, 6:57 p.m.