Triple
T12389320
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roy Cohn in Angels in America (Broadway revival) |
E295950
|
entity |
| Predicate | claimsToHave |
P32091
|
FINISHED |
| Object | liver cancer |
—
|
LITERAL 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: liver cancer | Statement: [Roy Cohn in Angels in America (Broadway revival), claimsToHave, liver cancer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: claimsToHave Context triple: [Roy Cohn in Angels in America (Broadway revival), claimsToHave, liver cancer]
-
A.
claimsToBe
chosen
Indicates that one entity asserts or declares itself to have a particular identity, role, or property, regardless of whether this assertion is true.
-
B.
claimsToMark
Indicates that one entity asserts or alleges that it has marked, labeled, or designated another entity in some specified way.
-
C.
claimsToDescribe
Indicates that one entity asserts that it provides an accurate or valid description of another entity or concept.
-
D.
claimsToFollow
Indicates that one entity asserts or professes adherence to the principles, rules, or leadership of another entity.
-
E.
hasClaimOn
Indicates that one entity holds a right, entitlement, or demand over another entity or its resources.
- F. None of above.
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_69d6ad9e653c8190b1473c860ee53dae |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d93fcf6aa8819080c9a2407a72db2e |
completed | April 10, 2026, 6:22 p.m. |
| PD | Predicate disambiguation | batch_69d93ed256788190b704cad171a4824e |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:54 p.m.