Triple
T4517311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Felix Leiter |
E103181
|
entity |
| Predicate | recursThroughout |
P54121
|
FINISHED |
| Object | multiple James Bond novels |
—
|
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: multiple James Bond novels | Statement: [Felix Leiter, recursThroughout, multiple James Bond novels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recursThroughout Context triple: [Felix Leiter, recursThroughout, multiple James Bond novels]
-
A.
recurs
Indicates that an event, condition, or pattern happens again, often repeatedly or at regular intervals, after having occurred before.
-
B.
recursIn
chosen
Indicates that an event, pattern, or entity appears repeatedly or returns multiple times within a given context, sequence, or timeframe.
-
C.
recurrence
Indicates that an event, condition, or state happens again or repeatedly over time, often after a period of absence or resolution.
-
D.
recurringDuring
Indicates that an event or state happens repeatedly within the time span or context defined by another event or interval.
-
E.
recites
Indicates that one entity verbally delivers or repeats from memory the words, text, or performance associated with another 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_69bd43dba59881908cf59b31df8c7ae1 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd572933408190b67c4ef6a7babe75 |
completed | March 20, 2026, 2:18 p.m. |
| PD | Predicate disambiguation | batch_69bd521abea48190b3e758a1f98dd55e |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:02 p.m.