Triple
T14984017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Philadelphia Naval Shipyard |
E373653
|
entity |
| Predicate | employedDuringPeak |
P23435
|
FINISHED |
| Object | over 40,000 workers |
—
|
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: over 40,000 workers | Statement: [Philadelphia Naval Shipyard, employedDuringPeak, over 40,000 workers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: employedDuringPeak Context triple: [Philadelphia Naval Shipyard, employedDuringPeak, over 40,000 workers]
-
A.
employedTo
Indicates that one entity is hired or engaged to perform work, services, or duties for another entity.
-
B.
employedThrough
Indicates that an entity holds a job or work position by means of, or via the arrangement of, another entity (such as an agency, contractor, or intermediary).
-
C.
peakEmployment
chosen
Indicates that an entity has reached its highest level of employment or workforce size during a specified period.
-
D.
hasOccupationDuringStory
Indicates that an entity holds or performs a particular occupation or job role during the time span covered by the story.
-
E.
workedAs
Indicates that an entity held a particular job, role, or position, performing work in that capacity.
- 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_69d85ccc84388190aa151e5173370c8d |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded6ff4a7c8190ab7554f3a1a09b67 |
completed | April 15, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69de9a6169b48190a679609febd2d0e3 |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:52 a.m.