Triple
T13977725
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Austin |
E336228
|
entity |
| Predicate | timeWithFreddieMercury |
P92173
|
FINISHED |
| Object | remained close after end of romantic relationship |
—
|
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: remained close after end of romantic relationship | Statement: [Mary Austin, timeWithFreddieMercury, remained close after end of romantic relationship]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeWithFreddieMercury Context triple: [Mary Austin, timeWithFreddieMercury, remained close after end of romantic relationship]
-
A.
endTime (spouse: Michael Jackson)
Indicates the time at which the marital relationship with Michael Jackson concluded.
-
B.
sting
Indicates inflicting a sharp, piercing pain or wound, typically by means of a pointed body part or object.
-
C.
זמנם
chosen
Indicates a relationship involving the time allotted to, belonging to, or associated with certain entities (e.g., “their time”).
-
D.
performedOnTourWith
Indicates that one entity carried out a tour in conjunction with, or as part of, another entity’s tour.
-
E.
isPosthumousTributeTo
Indicates that something (such as a work, event, or honor) is created or given as a tribute to a person after that person has died.
- 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_69d81c639e808190a0e4b4f3d31c6a59 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2e9fc7248190a9f26e253286ac3c |
completed | April 14, 2026, 12:10 p.m. |
| PD | Predicate disambiguation | batch_69dd465a21408190b912a42c50ffa0d9 |
completed | April 13, 2026, 7:39 p.m. |
Created at: April 9, 2026, 10:18 p.m.