Triple
T25725243
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | royal troops of Henry III |
E645099
|
entity |
| Predicate | outcomeOfAttempt |
P59870
|
FINISHED |
| Object | failure to secure Paris |
—
|
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: failure to secure Paris | Statement: [royal troops of Henry III, outcomeOfAttempt, failure to secure Paris]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: outcomeOfAttempt Context triple: [royal troops of Henry III, outcomeOfAttempt, failure to secure Paris]
-
A.
outcomeOfTrial
Indicates that a particular result or verdict is produced as the consequence of a specific trial or legal proceeding.
-
B.
outcomeOf
chosen
Indicates that one entity is the result, consequence, or product that arises from another entity, event, or process.
-
C.
missionOutcome
Indicates the result or consequence of a mission, specifying whether and how the mission’s objectives were achieved or failed.
-
D.
initialOutcome
Indicates the result or state that first occurs at the beginning of a process, event, or interaction, before any subsequent changes or outcomes.
-
E.
wasTriedAt
Indicates that a legal case or judicial proceeding involving an entity took place at a specific court or location.
- 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_69e77e8476fc8190bd5e9d05b89fad0a |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f600c18a14819081b5914dd3b0f9cf |
completed | May 2, 2026, 1:48 p.m. |
| PD | Predicate disambiguation | batch_69f5f7fba5248190945acf1561280799 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 21, 2026, 10:17 p.m.