Triple
T23218008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TS 31-series |
E580803
|
entity |
| Predicate | focusesOn |
P31
|
FINISHED |
| Object | ISIM |
—
|
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: ISIM | Statement: [TS 31-series, focusesOn, ISIM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ISIM Context triple: [TS 31-series, focusesOn, ISIM]
-
A.
ISIM
chosen
ISIM is the Integrated Science Instrument Module of the James Webb Space Telescope, housing and supporting its primary scientific instruments for observing the universe.
-
B.
SIMID
SIMID (Secure Interactive Media Interface Definition) is a digital advertising standard that defines how interactive video ads communicate and operate within video players across platforms.
-
C.
ISIR
ISIR is a research institute focused on advancing scientific and industrial technologies through interdisciplinary research and innovation.
-
D.
Simm
Simm is an English surname most notably associated with actor John Simm, known for his roles in British television and film.
-
E.
SIIMA
SIIMA is a major annual awards ceremony that honors excellence in South Indian cinema across multiple regional film industries.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2460389408190be74f41d217799a9 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1916653f08190a7dcbc659c6b6a25 |
completed | April 29, 2026, 5:04 a.m. |
Created at: April 17, 2026, 4:08 p.m.