Triple
T34284951
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manila Film Center |
E879706
|
entity |
| Predicate | constructionAccidentCasualties |
P72408
|
FINISHED |
| Object | multiple construction workers killed |
—
|
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: multiple construction workers killed | Statement: [Manila Film Center, constructionAccidentCasualties, multiple construction workers killed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: constructionAccidentCasualties Context triple: [Manila Film Center, constructionAccidentCasualties, multiple construction workers killed]
-
A.
constructionAccidentFatalities
chosen
Indicates that a construction-related accident resulted in one or more fatalities.
-
B.
railDisasterCasualties
Indicates the number of people killed or injured as a result of a specific rail disaster.
-
C.
primaryCasualtiesFrom
Indicates that an entity is the main source or cause of the casualties experienced by another entity.
-
D.
resultOfAccident
Indicates that something exists or occurs as a consequence or outcome of an accident.
-
E.
additionalDeathsRelatedToAccident
Indicates that there were extra fatalities occurring as a consequence of the accident beyond any initially recorded or primary deaths.
- 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_69f349b5f6648190b9420d94a4cd16e0 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69fd3a69f1e08190a11aed015bff0858 |
completed | May 8, 2026, 1:20 a.m. |
| PD | Predicate disambiguation | batch_69fd39124180819080ca7911d3515d6d |
completed | May 8, 2026, 1:14 a.m. |
Created at: May 1, 2026, 1:57 a.m.