Triple
T26673204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Life Scientific |
E672388
|
entity |
| Predicate | interviewerName |
P40000
|
FINISHED |
| Object | Jim Al-Khalili |
—
|
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: Jim Al-Khalili | Statement: [The Life Scientific, interviewerName, Jim Al-Khalili]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: interviewerName Context triple: [The Life Scientific, interviewerName, Jim Al-Khalili]
-
A.
interviewedBy
chosen
Indicates that an entity is the subject of an interview conducted by another entity.
-
B.
transcribedName
Indicates that one entity is a written or phonetic rendering of another entity’s name, typically adapted to a different script, language, or transcription system.
-
C.
nameOf
Indicates that one entity is the name or designation of another entity.
-
D.
narratorCharacterName
Indicates that a given character is the one serving as the narrator, and specifies the name used for that narrator.
-
E.
collaboratorName
Indicates that the predicate specifies the name of a person or entity who collaborates with another in some shared activity or project.
- 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_69eecda00a9c8190b2691f4d89db03b6 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f6bbf6e33c819086e5176d64e7a614 |
completed | May 3, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6b1e6c8190adf9d6a257e0b744 |
completed | May 3, 2026, 3 a.m. |
Created at: April 27, 2026, 3:14 a.m.