Triple
T4095909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IP |
E87819
|
entity |
| Predicate | associatedCompany |
P629
|
FINISHED |
| Object | International Paper Company |
E15200
|
NE 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: International Paper Company | Statement: [IP, associatedCompany, International Paper Company]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: International Paper Company Context triple: [IP, associatedCompany, International Paper Company]
-
A.
International Paper
chosen
International Paper is a leading global producer of renewable fiber-based packaging, pulp, and paper products.
-
B.
Georgia-Pacific
Georgia-Pacific is a major American pulp and paper company known for producing tissue, packaging, building products, and related chemicals.
-
C.
UPM
UPM is the Polytechnic University of Madrid, a leading Spanish public university specializing in engineering, architecture, and technology.
-
D.
Weyerhaeuser Company
Weyerhaeuser Company is a major American timberland and forest products company, historically one of the world’s largest private owners of softwood timber.
-
E.
Kimberly-Clark Corporation
Kimberly-Clark Corporation is a multinational personal care company best known for brands such as Kleenex, Huggies, and Scott paper products.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69aed94564cc8190a9c1457daedb6e7f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefcddd76c81909fbf5db1f5d91a14 |
completed | March 9, 2026, 5:01 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b589d825c48190b4208b0502c257bb |
completed | March 14, 2026, 4:16 p.m. |
Created at: March 9, 2026, 3:40 p.m.