Triple
T25056848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeriba Shigan |
E627541
|
entity |
| Predicate | relationshipTypeWith Willis Davidge |
P173661
|
FINISHED |
| Object | from enemies to friends |
—
|
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: from enemies to friends | Statement: [Jeriba Shigan, relationshipTypeWith Willis Davidge, from enemies to friends]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWith Willis Davidge Context triple: [Jeriba Shigan, relationshipTypeWith Willis Davidge, from enemies to friends]
-
A.
relationshipTypeWith Ty Davis Jr.
Indicates the specific nature or category of the relationship that an entity has with Ty Davis Jr.
-
B.
relationshipTypeWithWill Freeman
Indicates the specific nature or category of the relationship that an entity has with Will Freeman.
-
C.
relationshipTypeWithNickWells
Indicates the specific nature or category of relationship that an entity has with Nick Wells.
-
D.
relationshipTypeWith Sebastian Wilder
Indicates the specific nature or category of relationship that an entity has with Sebastian Wilder.
-
E.
relationshipTypeWith W. O. Gant
Indicates the specific nature or category of relational connection that an entity has with W. O. Gant.
- 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_69e2ff2c45f48190afa28369f1df6786 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f6b9a84ff88190ab5a71f7ef1e0dac |
completed | May 3, 2026, 2:57 a.m. |
| PD | Predicate disambiguation | batch_69f6b626120c819097c9ad04487570d7 |
completed | May 3, 2026, 2:42 a.m. |
| PDg | Predicate description generation | batch_69f6b8fe147881908ba17483c7b13f05 |
completed | May 3, 2026, 2:54 a.m. |
Created at: April 18, 2026, 6:09 a.m.