Triple
T20405111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kista |
E500446
|
entity |
| Predicate | hasMajorCompany |
P588
|
FINISHED |
| Object | IBM offices |
—
|
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: IBM offices | Statement: [Kista, hasMajorCompany, IBM offices]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IBM offices Context triple: [Kista, hasMajorCompany, IBM offices]
-
A.
LinkedIn headquarters
LinkedIn headquarters is the main corporate office of the professional networking platform LinkedIn, located in Sunnyvale, California.
-
B.
IBM
chosen
IBM is a multinational technology and consulting company known for its pioneering work in computer hardware, software, and enterprise services.
-
C.
World Office
World Office is the central administrative office that coordinates the global activities and communications of the Friends World Committee for Consultation, the international Quaker organization.
-
D.
Bristol-Myers Squibb offices
Bristol-Myers Squibb offices in Plainsboro Township are part of the global pharmaceutical company's corporate and research facilities, supporting its drug development and business operations.
-
E.
One Office
One Office is an integrated organizational model used in the UN’s “Delivering as One” approach to streamline internal operations and support more coherent, efficient country-level work.
- 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_69e0b4a81bec8190b69adfdc1336a015 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6799161c48190825eca3027d1aa51 |
completed | April 20, 2026, 7:08 p.m. |
Created at: April 16, 2026, 11:29 a.m.