Triple
T26682860
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jabez Stone |
E672660
|
entity |
| Predicate | makesDealWith |
P87080
|
FINISHED |
| Object | the Devil |
—
|
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: the Devil | Statement: [Jabez Stone, makesDealWith, the Devil]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: makesDealWith Context triple: [Jabez Stone, makesDealWith, the Devil]
-
A.
typeOfDeal
Indicates the specific category or nature of a deal or agreement that applies between entities.
-
B.
formsDealWith
chosen
Indicates that two or more entities establish a formal agreement or deal with each other.
-
C.
negotiationAssociatedWith
Indicates a relationship where a negotiation is connected to, involves, or is conducted by a particular entity (such as a person, organization, or group).
-
D.
hasDealingsIn
Indicates that an entity engages in activities, transactions, or business related to a particular domain, location, or subject.
-
E.
BigDealMechanic
Indicates a relationship where a mechanic is involved in handling, enabling, or being central to a particularly important or high-stakes deal or transaction.
- 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_69eecda13424819092b17942c4edf722 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f6173afcd881908356903457eef60e |
completed | May 2, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69f60b8bb0d08190ab5a9a2a8847c6f4 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 3:21 a.m.