Triple
T11088497
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terence MacSwiney |
E262185
|
entity |
| Predicate | hungerStrikeDuration |
P75958
|
FINISHED |
| Object | 74 days |
—
|
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: 74 days | Statement: [Terence MacSwiney, hungerStrikeDuration, 74 days]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hungerStrikeDuration Context triple: [Terence MacSwiney, hungerStrikeDuration, 74 days]
-
A.
numberOfDaysOnHungerStrike
chosen
Indicates the total count of days that an entity has continuously participated in a hunger strike.
-
B.
hungerStrikeEndDate
Indicates the date on which a hunger strike by the subject is concluded or terminated.
-
C.
startTimeOfHungerStrike
Indicates the specific time at which a hunger strike begins for the involved entity or event.
-
D.
fastingDuration
Indicates the length of time that an entity abstains from eating (and possibly drinking), typically as part of a fasting practice.
-
E.
followedInDeathOnHungerStrikeBy
Indicates that one individual died on hunger strike and was subsequently followed in death by another person who also died on hunger strike.
- 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_69d6aa9a40d88190a373e2c7e48285db |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d799e844b08190987c7c8e8d626510 |
completed | April 9, 2026, 12:22 p.m. |
| PD | Predicate disambiguation | batch_69d744185a5881909ba4cf151d1798ec |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:27 p.m.