Triple
T27348760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Hamer |
E684298
|
entity |
| Predicate | ledPosseAgainst |
P156962
|
FINISHED |
| Object | Clyde Barrow |
—
|
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: Clyde Barrow | Statement: [Frank Hamer, ledPosseAgainst, Clyde Barrow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ledPosseAgainst Context triple: [Frank Hamer, ledPosseAgainst, Clyde Barrow]
-
A.
ledAgainst
chosen
Indicates that one entity directed or commanded an opposing effort, campaign, or force against another entity.
-
B.
designedToOppose
Indicates that one entity is intentionally created or configured to counteract, resist, or work against another entity or process.
-
C.
opposesInLegend
Indicates a relationship where one entity is portrayed as an opponent or adversary of another within a legend or mythic narrative.
-
D.
ledPartyInElection
Indicates that one entity served as the leader or head of a political party during a specific election.
-
E.
opposingLeaders
Indicates that two leaders are in opposition to each other, typically representing rival or conflicting sides in a situation or context.
- 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_69ef1480a76481908684256ddd5bfda3 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f62ba5a110819092fe773ade8fec2e |
completed | May 2, 2026, 4:51 p.m. |
| PD | Predicate disambiguation | batch_69f623a91b9c8190b2e2fdbc55cb89b6 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 11:47 a.m.