Triple
T23239991
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cochecho Massacre of 1689 |
E581411
|
entity |
| Predicate | numberOfCaptives |
P36180
|
FINISHED |
| Object | approximately 29 English settlers taken captive |
—
|
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: approximately 29 English settlers taken captive | Statement: [Cochecho Massacre of 1689, numberOfCaptives, approximately 29 English settlers taken captive]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfCaptives Context triple: [Cochecho Massacre of 1689, numberOfCaptives, approximately 29 English settlers taken captive]
-
A.
captivesTaken
Indicates that one entity has taken another entity or group into captivity, holding them against their will.
-
B.
captivePopulation
Indicates that the entities are part of a population kept in captivity, such as in zoos, aquariums, or breeding facilities, rather than living in the wild.
-
C.
numberOfHostages
chosen
Indicates the quantity of hostages involved in a particular situation, event, or context.
-
D.
estimatedPrisoners
Indicates a relationship where a value represents the estimated number of prisoners associated with a particular entity or context.
-
E.
estimatedPrisonerCount
Indicates the estimated number of prisoners associated with a particular context, such as a location, time period, or event.
- 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_69e2460556f88190be1744a84a84173f |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f192ecc7e481908cac59df5c0deea1 |
completed | April 29, 2026, 5:11 a.m. |
| PD | Predicate disambiguation | batch_69effcdadec0819092ec1749ee453b4e |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:10 p.m.