Triple
T4177749
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Conservation International |
E86516
|
entity |
| Predicate | hasPartner |
P1136
|
FINISHED |
| Object | McDonald’s |
E173856
|
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: McDonald’s | Statement: [Conservation International, hasPartner, McDonald’s]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: McDonald’s Context triple: [Conservation International, hasPartner, McDonald’s]
-
A.
McDonald’s
chosen
McDonald’s is a global fast-food restaurant chain best known for its hamburgers, fries, and iconic Golden Arches branding.
-
B.
Yum! Brands
Yum! Brands is a major American fast-food corporation that owns and operates global restaurant chains such as KFC, Taco Bell, and Pizza Hut.
-
C.
Chick-fil-A
Chick-fil-A is a major American fast-food restaurant chain best known for its chicken sandwiches and strong presence in the Southern United States.
-
D.
White Castle
White Castle is a medieval stone fortress in Monmouthshire, Wales, notable for its well-preserved defensive earthworks and role in the border defenses of the Welsh Marches.
-
E.
Wahlburgers
Wahlburgers is an American casual-dining burger restaurant and bar chain co-owned by the Wahlberg family and featured in a reality TV series of the same name.
- 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_69aed93de98c8190ad838ce507b77c8a |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af02ec20fc8190b6f30576337e0ddc |
completed | March 9, 2026, 5:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b589f2d7988190b59f0f119f66c046 |
completed | March 14, 2026, 4:16 p.m. |
Created at: March 9, 2026, 3:45 p.m.