Triple
T23486432
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bill Campbell |
E570545
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | Claris |
—
|
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: Claris | Statement: [Bill Campbell, employer, Claris]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Claris Context triple: [Bill Campbell, employer, Claris]
-
A.
Claris
chosen
Claris is a software company best known for developing productivity and database applications, including the FileMaker platform and related tools.
-
B.
Claris
Claris is a small rural settlement and main service hub on Great Barrier Island in New Zealand, featuring the island’s primary airfield and basic visitor amenities.
-
C.
Lotus Word Pro
Lotus Word Pro is a word processing application developed by Lotus as part of the Lotus SmartSuite office productivity package.
-
D.
Bravo word processor
The Bravo word processor was an early WYSIWYG text-editing program developed at Xerox PARC for the Alto computer, pioneering many concepts used in modern word processing.
-
E.
Ashton-Tate
Ashton-Tate was a prominent American software company best known for its dBASE database management system, which was a leading product in the personal computer software market during the 1980s.
- 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_69e245b0b01481908f636939bedd804c |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a754825481909b005ca5654c3159 |
completed | April 29, 2026, 6:38 a.m. |
Created at: April 17, 2026, 6:04 p.m.